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

    Neuronpedia

    INDEX
    Explanations

    currency

    np_max-act · gemini-2.0-flash

    This neuron does not detect any specific patterns—it remains inactive (zero activation) across all inputs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     trained
    -0.07
     cat
    -0.06
    .setCharacter
    -0.06
    fuse
    -0.06
     gps
    -0.06
     orient
    -0.06
     appName
    -0.06
     sü
    -0.06
     freund
    -0.06
    úmeros
    -0.06
    POSITIVE LOGITS
     cljs
    0.07
    .VK
    0.07
    ्थ
    0.07
     Ner
    0.06
     قتل
    0.06
    beiten
    0.06
    wind
    0.06
    meter
    0.06
    ชนะ
    0.06
    .handleChange
    0.06
    Act Density 0.030%

    No Known Activations