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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting numeric tokens (especially numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Roku
    -0.06
    etcode
    -0.06
    Navbar
    -0.06
     tela
    -0.06
     mur
    -0.06
    .CENTER
    -0.06
     Suppliers
    -0.06
    kontakte
    -0.06
    _NODE
    -0.06
    LU
    -0.06
    POSITIVE LOGITS
     announcing
    0.07
     inconsistent
    0.07
    _health
    0.07
    نام
    0.07
     проп
    0.07
    /spec
    0.06
     �
    0.06
    óc
    0.06
    .Stat
    0.06
     những
    0.06
    Act Density 0.038%

    No Known Activations