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

    Neuronpedia

    INDEX
    Explanations

    data entry/code

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals with decimal points (floating-point constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     μπορού
    -0.07
    _contact
    -0.06
    .ev
    -0.06
     نزد
    -0.06
     करत
    -0.06
     nelle
    -0.06
    lerden
    -0.06
     왔
    -0.05
    labilir
    -0.05
    にする
    -0.05
    POSITIVE LOGITS
    Orig
    0.06
     skim
    0.06
     Programs
    0.06
    _quality
    0.06
     self
    0.06
     asym
    0.06
    ille
    0.06
    nemonic
    0.06
     Gen
    0.06
     rnn
    0.06
    Act Density 0.008%

    No Known Activations