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

    Neuronpedia

    INDEX
    Explanations

    geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specialization
    -0.09
     singleton
    -0.08
    라고
    -0.07
     exclusivamente
    -0.07
    _DISABLED
    -0.07
     Rules
    -0.07
     pandemic
    -0.07
     Alle
    -0.07
    요
    -0.07
    라는
    -0.07
    POSITIVE LOGITS
     phénomène
    0.09
     wata
    0.08
     légumes
    0.08
    bbox
    0.08
     phenomenon
    0.08
     paire
    0.08
     krat
    0.08
    outine
    0.08
    .et
    0.08
     accompanied
    0.08
    Act Density 0.013%

    No Known Activations