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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exclusive
    -0.07
    ''"
    -0.06
    алося
    -0.06
     男
    -0.06
     Ş
    -0.06
    .STATE
    -0.06
     heavy
    -0.06
    because
    -0.06
     Chair
    -0.06
     tradition
    -0.06
    POSITIVE LOGITS
    (spell
    0.07
    овід
    0.06
     useCallback
    0.06
    เทศ
    0.06
    (Stream
    0.06
     fled
    0.06
     vas
    0.06
    deps
    0.06
    _lambda
    0.06
     січня
    0.06
    Act Density 0.009%

    No Known Activations