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

    Neuronpedia

    INDEX
    Explanations

    themes of self-sacrifice and duty towards one's country

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

    actions or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kregen
    -0.44
     interessanti
    -0.35
     asociado
    -0.33
     intenção
    -0.33
     échanges
    -0.32
     invitados
    -0.32
    gegangen
    -0.32
     variados
    -0.32
     AUSSI
    -0.31
     asociados
    -0.31
    POSITIVE LOGITS
     Infórmanos
    0.65
    arraycopy
    0.62
    ьаж
    0.62
    InjectAttribute
    0.61
    Personensuche
    0.61
    GEBURTSDATUM
    0.59
    AndEndTag
    0.58
    MIDDLEWARE
    0.56
     BrowserModule
    0.54
    rungsseite
    0.53
    Act Density 0.056%

    No Known Activations