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

    Neuronpedia

    INDEX
    Explanations

    certification status updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     типа
    0.49
     typu
    0.47
     estilo
    0.47
    款式
    0.46
     типу
    0.45
     rodzaju
    0.45
     naš
    0.44
     STYLE
    0.43
     carène
    0.43
     inglesa
    0.43
    POSITIVE LOGITS
     mainland
    0.42
     certification
    0.38
     promises
    0.38
    eligible
    0.37
     Mainland
    0.37
    validation
    0.37
    这部
    0.37
    certification
    0.36
     parties
    0.36
    主要
    0.35
    Act Density 0.000%

    No Known Activations