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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens—especially floating‐point constants.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _calibration
    -0.06
    queda
    -0.06
     implementing
    -0.06
    arse
    -0.06
    _pic
    -0.06
     Connectivity
    -0.06
    (transform
    -0.06
    _CBC
    -0.06
     mesel
    -0.06
    .When
    -0.06
    POSITIVE LOGITS
              
↵
    0.06
    yms
    0.06
    LayoutConstraint
    0.06
     yapılır
    0.06
    uint
    0.06
    hashtags
    0.06
     olduğuna
    0.06
    `"]↵
    0.06
    .clientY
    0.06
    cheduled
    0.06
    Act Density 0.080%

    No Known Activations