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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash

    This neuron detects pairs of asterisks (“**”) used as bold or strong-emphasis markers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     passionate
    -0.06
    NoArgsConstructor
    -0.06
    KeyEvent
    -0.06
    .bucket
    -0.06
    avorite
    -0.06
    _kb
    -0.06
    .sprites
    -0.06
     checks
    -0.06
    748
    -0.06
    kd
    -0.06
    POSITIVE LOGITS
    **
    0.09
     **
    0.08
     khi
    0.07
    -window
    0.07
    _MPI
    0.07
    elps
    0.07
    _symbols
    0.06
     ys
    0.06
     مهم
    0.06
    ########################
    0.06
    Act Density 0.001%

    No Known Activations