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

    Neuronpedia

    INDEX
    Explanations

    elements related to moral values and social justice themes

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

    principles and purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unknownFields
    -0.47
     propOrder
    -0.42
     dizaines
    -0.40
     uintptr
    -0.39
    Armando
    -0.37
    getActiveSheet
    -0.36
    例句
    -0.36
    unteer
    -0.35
     intoler
    -0.35
     CallOverrides
    -0.35
    POSITIVE LOGITS
     Instead
    0.60
     esternos
    0.59
     instead
    0.56
    Instead
    0.56
    principalTable
    0.53
    出版年
    0.52
     ModelExpression
    0.52
    instead
    0.52
     invece
    0.52
     فريبيس
    0.52
    Act Density 0.029%

    No Known Activations