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

    Neuronpedia

    INDEX
    Explanations

    punctuation or symbols indicating a continuation or a reference in text

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

    » find out more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.54
    paravant
    -0.47
     Theſe
    -0.46
    LEEP
    -0.44
     referrerpolicy
    -0.44
    ization
    -0.40
     couvercle
    -0.39
     getConnection
    -0.39
    windowFixed
    -0.39
    pagnole
    -0.39
    POSITIVE LOGITS
     »
    1.78
    »
    1.18
    »»
    1.14
     ».
    1.10
     »,
    1.09
     »>
    1.02
    .»
    0.96
    !»
    0.92
     »)
    0.91
    ?»
    0.90
    Act Density 0.005%

    No Known Activations