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

    Neuronpedia

    INDEX
    Explanations

    past roles or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নিজেদের
    0.39
    <unused46>
    0.37
    ئر
    0.33
     می‌توانید
    0.33
    णियों
    0.32
     utilizamos
    0.32
     フェ
    0.32
     splatter
    0.32
     우리는
    0.32
     Ketch
    0.31
    POSITIVE LOGITS
     a
    0.56
    the
    0.53
     the
    0.50
     called
    0.48
     summoned
    0.48
    also
    0.46
    a
    0.46
    appointed
    0.46
     awarded
    0.45
    an
    0.44
    Act Density 0.043%

    No Known Activations