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

    Neuronpedia

    INDEX
    Explanations

    references to Earth and environmental themes

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

    Following words such as "as", "is", or ":"

    np_acts-logits-general · gemini-2.0-flash

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    -0.64
    ValueStyle
    -0.58
     (“
    -0.56
    ########.
    -0.55
     subsequently
    -0.51
     ultimately
    -0.50
     Subsequently
    -0.49
     OFDb
    -0.49
     posteriormente
    -0.48
     pihaknya
    -0.48
    POSITIVE LOGITS
    ."
    0.84
    DockStyle
    0.82
    …"
    0.81
    ?"
    0.81
     tonight
    0.78
    ..."
    0.77
     daqui
    0.76
    !"
    0.75
    -”
    0.75
    —”
    0.74
    Act Density 0.344%

    No Known Activations