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

    Neuronpedia

    INDEX
    Explanations

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    疾患
    0.36
    IRCONIUM
    0.36
    boldsymbol
    0.36
     функции
    0.36
    Equation
    0.35
    culoskeletal
    0.35
    halation
    0.34
    mogorov
    0.34
     recrystall
    0.34
     наличие
    0.34
    POSITIVE LOGITS
     몇
    0.45
     three
    0.44
     Three
    0.42
     여러
    0.40
     तीन
    0.40
     दो
    0.38
     kilka
    0.38
     사례
    0.38
    TestData
    0.37
     Beberapa
    0.37
    Act Density 0.377%

    No Known Activations