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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash

    The neuron specializes in detecting floating-point numeric literals (decimal numbers) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     incomplete
    -0.08
    eria
    -0.07
    ebin
    -0.07
    ojí
    -0.07
    ाद
    -0.06
    ,double
    -0.06
    tube
    -0.06
    hetic
    -0.06
     sill
    -0.06
     metropolitan
    -0.06
    POSITIVE LOGITS
    ERSHEY
    0.07
     роки
    0.06
    ''↵
    0.06
    .AddWithValue
    0.06
    Tips
    0.06
    cls
    0.06
     MagicMock
    0.06
     засобів
    0.06
     Debate
    0.06
     convin
    0.06
    Act Density 0.007%

    No Known Activations