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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash

    The neuron responds to underscore characters, particularly those in license filename/version strings (e.g. "LICENSE_1_0.txt").

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    821
    -0.07
     vůbec
    -0.06
     �
    -0.06
     Histogram
    -0.06
     admire
    -0.06
    .org
    -0.06
    ading
    -0.06
    YYYY
    -0.06
     powder
    -0.06
    NEL
    -0.06
    POSITIVE LOGITS
     I
    0.07
    _vertices
    0.07
    _TRNS
    0.07
    _do
    0.06
     vẻ
    0.06
     Revolutionary
    0.06
    .DataGridViewCellStyle
    0.06
    	be
    0.06
     Điện
    0.06
    库
    0.06
    Act Density 0.001%

    No Known Activations