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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric literal tokens (especially floating‐point/decimal constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .LogWarning
    -0.06
    .ResumeLayout
    -0.06
    _car
    -0.06
     놀
    -0.06
    _ORIENTATION
    -0.06
     Hornets
    -0.06
     Bar
    -0.06
    .scalablytyped
    -0.06
     مض
    -0.06
     billionaires
    -0.06
    POSITIVE LOGITS
     cushions
    0.07
    首页
    0.06
     signify
    0.06
     blames
    0.06
    ขว
    0.06
     intermitt
    0.06
    glyphicon
    0.06
    .addElement
    0.06
     few
    0.06
     cuid
    0.06
    Act Density 0.004%

    No Known Activations