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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -mm
    -0.07
     focal
    -0.06
    Steel
    -0.06
     Authors
    -0.06
     fame
    -0.06
     flashes
    -0.06
    attach
    -0.06
    _pattern
    -0.06
    MEA
    -0.06
    oni
    -0.06
    POSITIVE LOGITS
     shocked
    0.06
     удар
    0.06
     TOK
    0.06
     продолж
    0.06
     срав
    0.06
    enção
    0.06
    ’nda
    0.06
     España
    0.06
     Comey
    0.06
    anlar
    0.06
    Act Density 0.019%

    No Known Activations