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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    This neuron responds to the asterisk character used as a section or footnote marker.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     RestClient
    -0.06
     Thatcher
    -0.06
    йте
    -0.06
    -T
    -0.06
     Brigade
    -0.06
     Phy
    -0.06
     synth
    -0.06
    _mgmt
    -0.06
     nud
    -0.06
     ASF
    -0.06
    POSITIVE LOGITS
    estimated
    0.07
     veloc
    0.07
     regularization
    0.06
     uży
    0.06
    iationException
    0.06
    Timing
    0.06
    �에
    0.06
     tarea
    0.06
    .aw
    0.06
    ному
    0.06
    Act Density 0.001%

    No Known Activations