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

    Neuronpedia

    INDEX
    Explanations

    programming code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ান্দ
    1.21
    nourished
    1.09
    亼
    1.06
     Thom
    1.04
    ⎞
    1.04
     champagne
    1.03
     SEL
    1.03
     Momo
    1.01
    ibili
    1.01
    ュ
    1.01
    POSITIVE LOGITS
    ড
    1.09
    を参照
    1.06
    s
    1.05
     случаях
    1.03
    не
    1.03
     Designation
    0.98
     assertEquals
    0.94
    drawString
    0.94
     acyl
    0.93
    ubic
    0.93
    Act Density 0.004%

    No Known Activations