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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forces
    -0.08
    eper
    -0.08
     Tone
    -0.08
     festive
    -0.08
     forças
    -0.08
     creciendo
    -0.07
     adolescentes
    -0.07
     movimento
    -0.07
     indruk
    -0.07
     crescer
    -0.07
    POSITIVE LOGITS
     inverse
    0.11
    .inverse
    0.09
     reverse
    0.09
    _inverse
    0.08
     reversed
    0.08
     negatively
    0.08
    Inverse
    0.08
    .C
    0.08
    inverse
    0.08
     IO
    0.08
    Act Density 0.015%

    No Known Activations