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

    Neuronpedia

    INDEX
    Explanations

    input validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     изготовления
    1.12
    Тре
    1.07
     الحال
    1.02
    InputField
    1.01
    Ин
    1.01
    Ар
    1.00
    Кла
    1.00
    Эта
    0.95
    گ
    0.95
    们
    0.94
    POSITIVE LOGITS
    ting
    1.34
    rechte
    1.26
    ح
    1.17
    াধিকার
    1.16
    ಾನ್
    1.15
    ichtet
    1.13
     Producing
    1.12
    orant
    1.09
    isierte
    1.08
     Herzen
    1.07
    Act Density 0.119%

    No Known Activations