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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “For” (and similar tokens) when it begins informational sign-off lines like “For more information, contact…”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ervlet
    -0.07
    ele
    -0.07
    12
    -0.07
     renting
    -0.07
    yped
    -0.07
    Do
    -0.06
    repo
    -0.06
    inkel
    -0.06
    iyi
    -0.06
    Letter
    -0.06
    POSITIVE LOGITS
    $request
    0.07
    =current
    0.07
    _proto
    0.06
    :min
    0.06
     atrib
    0.06
    唯一
    0.06
     at
    0.06
     kullanı
    0.06
    .band
    0.06
     bilgileri
    0.06
    Act Density 0.012%

    No Known Activations