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

    Neuronpedia

    INDEX
    Explanations

    Muscles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Пра
    -0.07
     PLA
    -0.06
     соглас
    -0.06
     Decrypt
    -0.06
     využí
    -0.06
    _similarity
    -0.06
     Orta
    -0.06
     началь
    -0.06
     Coğraf
    -0.06
    /non
    -0.06
    POSITIVE LOGITS
    uts
    0.07
    ashed
    0.07
    ache
    0.06
    ,Yes
    0.06
    .keySet
    0.06
    ied
    0.06
     slož
    0.06
    Continue
    0.06
     minHeight
    0.06
    cut
    0.06
    Act Density 0.034%

    No Known Activations