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

    Neuronpedia

    INDEX
    Explanations

    mentions of harmful or negative impacts

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

    harmful or destructive consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorizaciones
    -0.66
    yntaxException
    -0.64
     Мексичка
    -0.59
    oneofs
    -0.59
    LookAnd
    -0.55
     Aufenthalt
    -0.55
     ujednoznacz
    -0.55
    HostException
    -0.52
    rungsseite
    -0.52
    orance
    -0.51
    POSITIVE LOGITS
     damaging
    1.55
     destructive
    0.99
    dama
    0.93
     detrimental
    0.91
     harmful
    0.88
     injurious
    0.81
     Dama
    0.79
    destructive
    0.78
     devastating
    0.77
     merusak
    0.75
    Act Density 0.018%

    No Known Activations