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 strongly activates on question-related tokens (e.g. “what,” “you,” “are,” “asking,” “for”) and so mainly detects when the user is phrasing or clarifying a question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .NVarChar
    -0.06
    534
    -0.06
    (bitmap
    -0.06
    耳
    -0.06
     розум
    -0.06
    -shadow
    -0.06
     徒
    -0.06
    .printStackTrace
    -0.06
     Cody
    -0.06
    avě
    -0.06
    POSITIVE LOGITS
    \R
    0.07
    'M
    0.06
    _COLL
    0.06
    /km
    0.06
     `.
    0.06
     eldre
    0.06
     espera
    0.06
    _FILENO
    0.06
     humming
    0.06
    	container
    0.06
    Act Density 0.030%

    No Known Activations