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

    Neuronpedia

    INDEX
    Explanations

    pantry staples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इट्स
    0.64
    㕵
    0.61
     It
    0.60
    ان
    0.60
    िंग
    0.57
    磯
    0.55
    <unused243>
    0.55
    ెంట్
    0.55
     bebas
    0.54
    س
    0.54
    POSITIVE LOGITS
    at
    1.09
    ad
    0.93
    if
    0.83
    ব
    0.79
    4
    0.77
    it
    0.76
    for
    0.74
    5
    0.73
    President
    0.72
    B
    0.70
    Act Density 0.003%

    No Known Activations