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

    Neuronpedia

    INDEX
    Explanations

    code/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ybrid
    -0.07
     ND
    -0.07
    .Identity
    -0.07
     Lie
    -0.07
    -0.07
    emi
    -0.07
     Lite
    -0.06
     alleviate
    -0.06
     Н
    -0.06
    movie
    -0.06
    POSITIVE LOGITS
     Tato
    0.07
     Combine
    0.06
    غاز
    0.06
    Combine
    0.06
    _ART
    0.06
    (\$
    0.06
     board
    0.06
    े
    0.06
    !important
    0.06
     strong
    0.06
    Act Density 0.071%

    No Known Activations