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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fh
    -0.07
    دار
    -0.07
     subjected
    -0.06
    primir
    -0.06
     sabotage
    -0.06
     SqlDbType
    -0.06
    Republican
    -0.06
    Oregon
    -0.06
    every
    -0.06
    -0.06
    POSITIVE LOGITS
    21
    0.06
     설명
    0.06
    ejs
    0.06
     сух
    0.06
    νού
    0.06
    19
    0.06
    ्छ
    0.06
     questioned
    0.06
    (','
    0.06
    numer
    0.06
    Act Density 0.001%

    No Known Activations