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

    Neuronpedia

    INDEX
    Explanations

    group comparisons

    np_max-act · gemini-2.0-flash

    This neuron activates on the labels and identifiers of study groups (e.g., “Group I,” “II,” “A,” “B,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    لام
    -0.07
    ysql
    -0.06
    train
    -0.06
    ollah
    -0.06
    rain
    -0.06
    El
    -0.06
     kesinlikle
    -0.06
     Boeh
    -0.06
     einem
    -0.06
     eta
    -0.06
    POSITIVE LOGITS
     rusty
    0.07
     retract
    0.06
     bergen
    0.06
     خاطر
    0.06
    _PUT
    0.06
    وية
    0.06
     //}↵↵
    0.06
     типу
    0.06
    <{↵
    0.06
    :view
    0.06
    Act Density 0.040%

    No Known Activations