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

    Neuronpedia

    INDEX
    Explanations

    brackets/quotes

    np_max-act · gemini-2.0-flash

    The neuron does not detect or respond to any ordinary text tokens—it remains inactive and thus finds nothing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    了解
    -0.07
    ４
    -0.06
    12
    -0.06
    974
    -0.06
    奪
    -0.06
    คน
    -0.06
    รณ
    -0.06
    'aff
    -0.06
    大会
    -0.06
    BBC
    -0.06
    POSITIVE LOGITS
    iyesi
    0.07
    λλι
    0.07
    .EditText
    0.07
    teri
    0.07
    atum
    0.06
    düğ
    0.06
    _OVERFLOW
    0.06
    .getText
    0.06
    mente
    0.06
     interfer
    0.06
    Act Density 0.096%

    No Known Activations