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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Evaluation
    -0.06
    Alg
    -0.06
    Во
    -0.06
     nez
    -0.06
    anglicky
    -0.06
     ut
    -0.06
     assistants
    -0.06
     Civil
    -0.06
    -variable
    -0.06
    ilis
    -0.06
    POSITIVE LOGITS
    serter
    0.07
    oire
    0.07
    ımızı
    0.07
    buttonShape
    0.07
    oenix
    0.07
    trecht
    0.07
     acheter
    0.06
    zdy
    0.06
     Murray
    0.06
    .TabPage
    0.06
    Act Density 0.013%

    No Known Activations