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

    Neuronpedia

    INDEX
    Explanations

    benefits, past, up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PAOK
    0.94
     Pelosi
    0.91
    Singolare
    0.88
     Ogni
    0.88
    CharArray
    0.87
     Chica
    0.87
    陥
    0.86
    ficha
    0.85
    Centro
    0.84
     Politik
    0.84
    POSITIVE LOGITS
    гда
    0.88
    ünü
    0.87
    チェア
    0.86
    با
    0.84
    dc
    0.80
    naie
    0.77
    //
    0.77
    ਸ
    0.76
    rior
    0.75
    𝗇
    0.75
    Act Density 0.000%

    No Known Activations