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

    Neuronpedia

    INDEX
    Explanations

    content related to cautionary statements and user communication

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

    statements followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.40
    ValueGenerated
    -0.35
    BeginInit
    -0.34
    entin
    -0.34
    wards
    -0.33
    直
    -0.33
    ACH
    -0.31
    addGap
    -0.31
     st
    -0.31
    diger
    -0.30
    POSITIVE LOGITS
     vœ
    0.54
     anún
    0.54
    Datuak
    0.52
    AndEndTag
    0.52
    WebElementEntity
    0.52
    Ещё
    0.52
     pérd
    0.51
    ArgsConstructor
    0.51
    Rhestr
    0.50
     sumpay
    0.49
    Act Density 0.003%

    No Known Activations