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

    Neuronpedia

    INDEX
    Explanations

    specific references to notable events and achievements related to films and actors

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

    years associated with wars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.90
     <=",
    -0.74
     للاسماء
    -0.73
     AssemblyCulture
    -0.71
     Chwiliwch
    -0.68
    DockStyle
    -0.68
    ロウィン
    -0.68
    RenderAtEndOf
    -0.68
    ThroughAttribute
    -0.68
    ftagPool
    -0.67
    POSITIVE LOGITS
     chiefly
    0.33
     primarily
    0.33
     become
    0.30
     mainly
    0.30
     becoming
    0.30
     characterized
    0.29
     υ
    0.29
     haci
    0.29
     became
    0.29
     مم
    0.28
    Act Density 0.011%

    No Known Activations