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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гули
    0.50
    Prints
    0.48
     discretized
    0.48
    toBytes
    0.45
    Implementation
    0.45
     radiations
    0.42
    კ
    0.42
    Decrease
    0.42
     giảm
    0.41
     Calculates
    0.41
    POSITIVE LOGITS
     Ert
    0.49
     scopes
    0.48
    ื่อง
    0.48
    โดย
    0.48
    is
    0.44
     BUSINESS
    0.44
    ل
    0.44
    ুম
    0.43
    商品の
    0.43
    ช่วง
    0.43
    Act Density 0.000%

    No Known Activations