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

    Neuronpedia

    INDEX
    Explanations

    job interview skills and preparation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.10
     it
    0.83
    د
    0.79
     on
    0.74
    น
    0.73
    م
    0.70
     the
    0.68
    ل
    0.68
    न
    0.66
     มัน
    0.64
    POSITIVE LOGITS
    (
    0.81
    x
    0.77
    th
    0.71
    at
    0.69
    A
    0.65
    B
    0.64
    ı
    0.64
    -
    0.63
    and
    0.63
    টা
    0.63
    Act Density 0.004%

    No Known Activations