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

    Neuronpedia

    INDEX
    Explanations

    standards

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numbers (tokens representing decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tomatoes
    -0.07
     خانه
    -0.07
    _generic
    -0.07
    (trace
    -0.06
     appreciate
    -0.06
    -week
    -0.06
    tracked
    -0.06
     used
    -0.06
     fluffy
    -0.06
    Pad
    -0.06
    POSITIVE LOGITS
     Ου
    0.07
    asz
    0.06
    lation
    0.06
    GNUC
    0.06
    DF
    0.06
     Becker
    0.06
    糖
    0.06
    sson
    0.06
     UIAlertController
    0.06
    tn
    0.06
    Act Density 0.023%

    No Known Activations