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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron identifies numeric literals—tokens consisting of digits (including decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     chest
    -0.07
    adioButton
    -0.06
    loggedin
    -0.06
    Modal
    -0.06
    струк
    -0.06
    لل
    -0.06
     waits
    -0.06
     мой
    -0.06
    DropDown
    -0.06
     multiline
    -0.06
    POSITIVE LOGITS
     vagy
    0.07
     rpm
    0.07
     +-
    0.06
     øns
    0.06
     salida
    0.06
    resolution
    0.06
     схем
    0.06
     genotype
    0.06
    losti
    0.06
    -facing
    0.06
    Act Density 0.009%

    No Known Activations