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

    Neuronpedia

    INDEX
    Explanations

    just a basic descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    1.82
    a
    1.80
    ه
    1.75
     it
    1.59
    ה
    1.57
    the
    1.53
    an
    1.52
    ال
    1.51
    ب
    1.51
    ان
    1.50
    POSITIVE LOGITS
     in
    0.95
     tendencia
    0.86
     battalion
    0.82
    <0x91>
    0.77
     compliance
    0.75
    ς
    0.75
    2
    0.73
    在
    0.73
    én
    0.70
    ją
    0.70
    Act Density 0.031%

    No Known Activations