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

    Neuronpedia

    INDEX
    Explanations

    document excerpts

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to tokens that look like floating‐point numbers (i.e. numeric tokens with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Το
    -0.08
     수가
    -0.07
    _String
    -0.07
    세
    -0.07
    olated
    -0.06
    Writes
    -0.06
     Prote
    -0.06
     &(
    -0.06
    _ING
    -0.06
    INV
    -0.06
    POSITIVE LOGITS
    -over
    0.07
     υπάρχ
    0.07
    !");↵
    0.07
     избав
    0.07
    "}}
    0.07
    .Tensor
    0.06
     może
    0.06
     INFORMATION
    0.06
     dří
    0.06
    想到
    0.06
    Act Density 0.000%

    No Known Activations