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

    Neuronpedia

    INDEX
    Explanations

    identifying himself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uws
    0.80
    тальян
    0.77
     acostumbr
    0.76
    gota
    0.75
     отказаться
    0.75
     explored
    0.71
    ías
    0.70
     adimensional
    0.70
     подели
    0.70
     Compute
    0.70
    POSITIVE LOGITS
    ל
    0.97
    り
    0.89
     ofthe
    0.87
    Muito
    0.85
    Trich
    0.82
    ซ์
    0.82
    기
    0.81
    jalanan
    0.79
    ขาย
    0.79
    饬
    0.79
    Act Density 0.000%

    No Known Activations