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

    Neuronpedia

    INDEX
    Explanations

    variation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nam
    -0.07
    获
    -0.07
    oria
    -0.07
    dh
    -0.06
    uits
    -0.06
    erap
    -0.06
     keyed
    -0.06
     Philadelphia
    -0.06
     ix
    -0.06
     Pole
    -0.06
    POSITIVE LOGITS
     textSize
    0.07
     myslí
    0.06
    ）は
    0.06
     strokeLine
    0.06
    幹線
    0.06
    ('<?
    0.06
    스를
    0.05
     EF
    0.05
     separat
    0.05
    .fragments
    0.05
    Act Density 0.420%

    No Known Activations