Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to making assertions or highlighting specific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Referring to something or calling attention to something

    np_acts-logits-general · gemini-2.0-flash

    pointing out or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.35
    Discografia
    -0.35
     dalamnya
    -0.32
     transf
    -0.32
     paix
    -0.32
    bcrypt
    -0.31
     Jahrhunderts
    -0.30
     Organ
    -0.30
     reactor
    -0.29
    InBackground
    -0.29
    POSITIVE LOGITS
    AndEndTag
    0.82
     pointing
    0.77
     pointed
    0.75
     highlighting
    0.75
     highlight
    0.72
    highlight
    0.72
     Highlight
    0.69
    pointed
    0.68
    pointing
    0.67
     importance
    0.66
    Act Density 0.257%

    No Known Activations