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

    Neuronpedia

    INDEX
    Explanations

    oranges and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Они
    0.90
     "~
    0.89
     ומ
    0.80
     הע
    0.78
     Yes
    0.78
     Durchführung
    0.78
     וא
    0.77
     వ
    0.77
     ifades
    0.77
     የተ
    0.77
    POSITIVE LOGITS
    .).
    0.69
    .\\
    0.67
    .]
    0.66
    이지만
    0.66
    .].
    0.65
    (
    0.61
    ).
    0.60
    ).”
    0.59
     nữa
    0.59
    itatively
    0.59
    Act Density 0.167%

    No Known Activations