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

    Neuronpedia

    INDEX
    Explanations

    secret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sai
    -0.07
     sito
    -0.07
     minced
    -0.07
     เห
    -0.07
     ProgressBar
    -0.06
     tts
    -0.06
    عداد
    -0.06
     illumination
    -0.06
    _UN
    -0.06
    "P
    -0.06
    POSITIVE LOGITS
     doubtful
    0.06
     violations
    0.06
    _af
    0.06
     vm
    0.06
    Elizabeth
    0.06
    교
    0.06
    osexual
    0.06
    hind
    0.06
    preter
    0.06
    .Version
    0.06
    Act Density 0.167%

    No Known Activations