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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting URL scheme tokens (e.g. “http”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ooks
    -0.07
    .Total
    -0.07
    lemma
    -0.06
    udios
    -0.06
    DetailsService
    -0.06
    iosity
    -0.06
    decode
    -0.06
    睛
    -0.06
    _AVAILABLE
    -0.06
     Debugger
    -0.06
    POSITIVE LOGITS
     南
    0.07
    .metroLabel
    0.07
    urger
    0.06
    [unit
    0.06
     anx
    0.06
     casing
    0.06
    estre
    0.06
    ืน
    0.06
    南
    0.06
    ่ละ
    0.06
    Act Density 0.008%

    No Known Activations