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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns and foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IC
    -0.08
     allocating
    -0.08
     mens
    -0.08
     рамках
    -0.07
     testosterone
    -0.07
     faux
    -0.07
    �
    -0.07
     drowning
    -0.07
    qqa
    -0.07
    ுகளை
    -0.07
    POSITIVE LOGITS
    .helpers
    0.07
     Hor
    0.07
     hardly
    0.07
    hor
    0.07
    ನ್ನು
    0.07
     ζ
    0.07
    Hor
    0.07
    acar
    0.07
    握
    0.07
    Nich
    0.07
    Act Density 0.116%

    No Known Activations