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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

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

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Order
    -0.07
    _ACK
    -0.06
    /pay
    -0.06
    jiště
    -0.06
     duct
    -0.06
     machen
    -0.06
    assing
    -0.06
     folds
    -0.06
     Refresh
    -0.06
    uilt
    -0.06
    POSITIVE LOGITS
    -categories
    0.08
     сфер
    0.07
     Cong
    0.07
    pleado
    0.07
     tokenize
    0.07
    لیل
    0.06
    yen
    0.06
    /projects
    0.06
    overall
    0.06
     constituent
    0.06
    Act Density 0.116%

    No Known Activations