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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in code snippets

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

    user prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )_/¯
    -0.49
    DockStyle
    -0.48
    nhof
    -0.39
    calipsis
    -0.39
    psis
    -0.39
     Leap
    -0.38
    luft
    -0.38
    брь
    -0.37
    IPMENT
    -0.37
    kai
    -0.37
    POSITIVE LOGITS
    makeText
    0.70
     <<<<<<<<<<<<<<
    0.62
    OGND
    0.57
    httphttps
    0.47
     Signalez
    0.47
     autorytatywna
    0.45
     actionMode
    0.45
    Bakgrunnsstoff
    0.43
    ьаж
    0.43
     “
    0.42
    Act Density 0.003%

    No Known Activations