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

    Neuronpedia

    INDEX
    Explanations

    Tactical nuclear weapons and combat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    0.75
     aloof
    0.69
    Οι
    0.67
    exhaustive
    0.66
    cross
    0.65
    feat
    0.64
    Escape
    0.64
    liferation
    0.64
     CAGR
    0.64
    traces
    0.63
    POSITIVE LOGITS
    𝙜
    0.77
    nesium
    0.72
    𝙠
    0.71
    तुम्हारा
    0.69
    𝙣
    0.69
    ور
    0.68
    ்த
    0.68
    ین
    0.68
    ين
    0.67
     gad
    0.66
    Act Density 0.006%

    No Known Activations