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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron primarily detects reference citations or numeric markers (e.g. bracketed reference numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     drv
    -0.07
     Buddh
    -0.06
    Что
    -0.06
    inz
    -0.06
    )에
    -0.06
    cache
    -0.06
    Routine
    -0.06
     Then
    -0.06
     failing
    -0.06
     Kak
    -0.06
    POSITIVE LOGITS
     {$
    0.07
    تر
    0.07
    mad
    0.06
     snakes
    0.06
    VBoxLayout
    0.06
     Rip
    0.06
    Bi
    0.06
    .IsDBNull
    0.06
     осві
    0.06
     ­
    0.06
    Act Density 0.001%

    No Known Activations