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

    Neuronpedia

    INDEX
    Explanations

    aka

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispersion
    -0.07
     thighs
    -0.07
     cosine
    -0.06
     rog
    -0.06
     formed
    -0.06
     Ubisoft
    -0.06
     az
    -0.06
    amber
    -0.06
     regulator
    -0.06
    ij
    -0.06
    POSITIVE LOGITS
    KA
    0.09
     harek
    0.07
    нення
    0.07
    ska
    0.07
     클
    0.07
    ka
    0.07
     Berk
    0.07
     felse
    0.07
    ську
    0.07
    buckets
    0.07
    Act Density 0.008%

    No Known Activations