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

    Neuronpedia

    INDEX
    Explanations

    python imports and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    主
    0.45
    胚
    0.44
    agedy
    0.41
    dns
    0.39
     குறைவாக
    0.38
     Hurst
    0.38
    坯
    0.38
    openqa
    0.38
     names
    0.37
     mains
    0.36
    POSITIVE LOGITS
    from
    0.46
    STITUTION
    0.45
    toler
    0.45
    port
    0.44
    Port
    0.44
    Quiet
    0.44
    PORT
    0.43
     tolerate
    0.41
     crib
    0.40
     Quiet
    0.40
    Act Density 0.250%

    No Known Activations