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

    Neuronpedia

    INDEX
    Explanations

    explicit consent or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seven
    0.51
     Mods
    0.47
     Seventeen
    0.47
     <
    0.46
     topped
    0.46
     Twenty
    0.45
     Rept
    0.44
     প্রদেশের
    0.44
     str
    0.44
     Cinemas
    0.43
    POSITIVE LOGITS
    dard
    0.51
    貥
    0.50
    rosine
    0.48
    bel
    0.46
    riterien
    0.46
     directo
    0.46
     депозиттик
    0.45
    ceğ
    0.45
    nton
    0.45
    önig
    0.45
    Act Density 0.005%

    No Known Activations