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

    Neuronpedia

    INDEX
    Explanations

    technical terms and foreign language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mary
    0.54
    ากร
    0.45
     Excessive
    0.45
     excessive
    0.44
    Mary
    0.44
     eher
    0.43
    ರಿಕ
    0.42
    InputValue
    0.42
     spilled
    0.42
     ಮಾರ
    0.42
    POSITIVE LOGITS
    救
    0.53
     fuerzas
    0.52
    ితే
    0.51
    ا
    0.48
     liberté
    0.48
    霓
    0.47
    ны
    0.46
    颐
    0.46
     lực
    0.46
    街
    0.46
    Act Density 0.000%

    No Known Activations