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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anı
    -0.06
    mkdir
    -0.06
    (selector
    -0.06
     balık
    -0.06
     Osc
    -0.06
    logy
    -0.06
    xdc
    -0.06
     fø
    -0.06
     ADS
    -0.06
     kapsamında
    -0.06
    POSITIVE LOGITS
     Northern
    0.07
    سم
    0.06
     OWNER
    0.06
    엄
    0.06
     incorporating
    0.06
    ENTS
    0.06
    coes
    0.06
     Tight
    0.06
    ight
    0.06
     помог
    0.06
    Act Density 0.045%

    No Known Activations