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

    Neuronpedia

    INDEX
    Explanations

    makes your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ethical
    0.45
     penampilan
    0.43
    एर
    0.42
     Axial
    0.40
    ਣੀ
    0.40
     கிறிஸ்துவின்
    0.40
     Regel
    0.39
    inent
    0.38
     mull
    0.38
    Appearance
    0.38
    POSITIVE LOGITS
     melhorar
    0.50
     動物
    0.49
     بم
    0.49
    荞
    0.48
     улуч
    0.47
     reservados
    0.46
     trabajos
    0.45
     동물
    0.45
     ө
    0.44
     ухуд
    0.44
    Act Density 0.000%

    No Known Activations