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

    Neuronpedia

    INDEX
    Explanations

    definitions

    np_max-act · gemini-2.0-flash

    This neuron activates on decimal numbers (tokens representing fractional numeric values, e.g. “0.249267578125”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     economies
    -0.07
    ora
    -0.07
    cus
    -0.07
     PhD
    -0.07
     Ministry
    -0.06
     PAD
    -0.06
    416
    -0.06
    .branch
    -0.06
    INI
    -0.06
     politics
    -0.06
    POSITIVE LOGITS
     соп
    0.07
     omitted
    0.07
    *↵↵
    0.06
     عنوان
    0.06
     Rek
    0.06
     kadın
    0.06
     Freed
    0.06
     जगह
    0.06
     لو
    0.06
    .Temp
    0.06
    Act Density 0.032%

    No Known Activations