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

    Neuronpedia

    INDEX
    Explanations

    references to exclusive groups and memberships

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

    belonging or being alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.38
     morire
    -0.31
    笔
    -0.30
     konflikt
    -0.29
     conflict
    -0.28
     massacre
    -0.28
    というもの
    -0.28
     chamada
    -0.27
    Ứng
    -0.27
     massacres
    -0.27
    POSITIVE LOGITS
    complexContent
    0.61
    complexType
    0.59
    writeFieldEnd
    0.52
     Signalez
    0.52
    ंदीखरीदारी
    0.52
     Italijani
    0.50
    joined
    0.50
     joined
    0.50
    ylvan
    0.50
    Club
    0.49
    Act Density 0.163%

    No Known Activations