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

    Neuronpedia

    INDEX
    Explanations

    Evaluating quantities relative to expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一个
    0.52
    ة
    0.49
    क
    0.49
    细胞
    0.48
    vä
    0.46
    米
    0.46
     hög
    0.46
    ベーション
    0.46
    规律
    0.44
    mimpi
    0.44
    POSITIVE LOGITS
     llamadas
    0.52
     llamada
    0.49
     PROFESSIONAL
    0.48
     संबोध
    0.48
     hebre
    0.46
     выну
    0.45
    ;$
    0.45
     menambah
    0.44
     estuv
    0.44
     salary
    0.44
    Act Density 0.004%

    No Known Activations