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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     niemand
    0.64
     deciding
    0.64
     drift
    0.64
    也就
    0.63
     resulting
    0.63
     defining
    0.61
     blending
    0.61
     inev
    0.61
     fate
    0.61
     decide
    0.61
    POSITIVE LOGITS
     Studies
    1.53
     studies
    1.41
    Studies
    1.39
     Studien
    1.31
    studies
    1.31
     STUDIES
    1.30
     estudos
    1.23
     Estudos
    1.13
     स्टडी
    1.11
     Estudios
    1.09
    Act Density 0.356%

    No Known Activations