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

    Neuronpedia

    INDEX
    Explanations

    dire needs or difficult situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.34
    т
    1.12
    д
    1.11
    يع
    0.95
    ט
    0.89
    ل
    0.89
    ز
    0.88
    ين
    0.88
    د
    0.86
    త
    0.86
    POSITIVE LOGITS
    dire
    0.99
     dire
    0.86
    7
    0.75
    2
    0.73
    henyl
    0.71
     sebenarnya
    0.70
    Dire
    0.69
     Dire
    0.67
     diperlukan
    0.66
     bukanlah
    0.65
    Act Density 0.000%

    No Known Activations