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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    The neuron flags special document-formatting markers and code-block delimiters (e.g. system/user headers, start/end tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (P
    -0.08
     خواه
    -0.06
    ("//*[@
    -0.06
    下去
    -0.06
    肌
    -0.06
    -0.06
     普
    -0.06
    .@
    -0.06
    够
    -0.06
     рекоменду
    -0.06
    POSITIVE LOGITS
     Mit
    0.08
    wahl
    0.07
    rets
    0.06
    Logout
    0.06
     Lowell
    0.06
     La
    0.06
     gün
    0.06
    Recorder
    0.06
    otty
    0.06
    .modal
    0.06
    Act Density 0.009%

    No Known Activations