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

    Neuronpedia

    INDEX
    Explanations

    independent, Laws, unique, wants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disconnecting
    0.52
    '
    0.51
    語
    0.49
     handicap
    0.49
    ने
    0.48
    リー
    0.47
     openness
    0.47
    َع
    0.45
     tooling
    0.45
    পল
    0.45
    POSITIVE LOGITS
     देणे
    0.55
     दिर
    0.52
    rarea
    0.52
    譞
    0.52
    н
    0.49
     הצ
    0.48
     Анали
    0.48
     Juda
    0.48
     Są
    0.48
     pode
    0.47
    Act Density 0.000%

    No Known Activations