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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oton
    -0.07
     کاری
    -0.06
    gal
    -0.06
    _cluster
    -0.06
    anas
    -0.06
    -fire
    -0.06
    enburg
    -0.06
    pickle
    -0.06
     orphan
    -0.06
    antasy
    -0.06
    POSITIVE LOGITS
     во
    0.07
    <Student
    0.06
     Blogger
    0.06
    ovíd
    0.06
     civilized
    0.06
     зак
    0.06
     TZ
    0.06
     noh
    0.06
    (inner
    0.06
    عب
    0.06
    Act Density 0.003%

    No Known Activations