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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific person's name

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

    explains or notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.61
    PostInfinity
    -0.60
    expandindo
    -0.56
    ValueStyle
    -0.56
     AssemblyTitle
    -0.56
    tagHelperRunner
    -0.56
    Autoritní
    -0.53
     myſelf
    -0.53
     itſelf
    -0.51
     iVar
    -0.50
    POSITIVE LOGITS
    IGENCE
    0.40
    JsonPropertyName
    0.36
     Erklärung
    0.35
    Composição
    0.35
     separados
    0.35
    pośred
    0.34
    ionales
    0.34
    iertamente
    0.33
    separation
    0.33
     Trennung
    0.32
    Act Density 0.155%

    No Known Activations