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

    Neuronpedia

    INDEX
    Explanations

    registry and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plunge
    -0.08
     पूरे
    -0.08
     Plush
    -0.08
    (cin
    -0.08
     thrilled
    -0.08
    (edge
    -0.08
     वस्त
    -0.08
     �
    -0.07
     primal
    -0.07
     filming
    -0.07
    POSITIVE LOGITS
     Kerry
    0.08
    http
    0.08
     acessar
    0.07
    klass
    0.07
    μμ
    0.07
    kan
    0.07
    \\.
    0.07
    ZZ
    0.07
    represent
    0.07
    Represent
    0.07
    Act Density 0.002%

    No Known Activations