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

    Neuronpedia

    INDEX
    Explanations

    Code/connections

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive and does not detect any particular pattern in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    picker
    -0.06
    .Per
    -0.06
    RecognitionException
    -0.06
    <long
    -0.06
    unwrap
    -0.06
     Serialize
    -0.06
     breakpoint
    -0.06
     ling
    -0.06
    _git
    -0.06
    Pair
    -0.06
    POSITIVE LOGITS
     Appears
    0.07
    иф
    0.07
    ardo
    0.07
    %");↵
    0.07
    ddy
    0.06
     nonsense
    0.06
    ोषण
    0.06
     POSSIBILITY
    0.06
     realistically
    0.06
    ，还
    0.06
    Act Density 0.013%

    No Known Activations