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

    Neuronpedia

    INDEX
    Explanations

    availability of data

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ="/">
    -0.07
    .setHorizontalAlignment
    -0.07
     Pew
    -0.06
    Io
    -0.06
    Cele
    -0.06
     zn
    -0.06
    ाइस
    -0.06
    ήμερα
    -0.06
    獲
    -0.06
    昇
    -0.06
    POSITIVE LOGITS
     sai
    0.07
    anker
    0.07
     tops
    0.07
    いに
    0.07
    overnment
    0.07
    út
    0.07
     karıştır
    0.06
     Login
    0.06
    어진
    0.06
    _description
    0.06
    Act Density 0.013%

    No Known Activations