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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     penchant
    -0.08
     marr
    -0.08
    gen
    -0.08
    aul
    -0.08
     Cheer
    -0.07
    mock
    -0.07
     concerns
    -0.07
    inations
    -0.07
     plateforme
    -0.07
     ties
    -0.07
    POSITIVE LOGITS
     sake
    0.09
     objetiva
    0.09
     объектив
    0.08
    .drawer
    0.08
     coherence
    0.08
     slaapkamer
    0.08
     попасть
    0.08
     להיות
    0.08
    objective
    0.08
    _kw
    0.07
    Act Density 0.016%

    No Known Activations