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

    Neuronpedia

    INDEX
    Explanations

    dates and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     same
    0.83
     invariance
    0.70
     ident
    0.70
     identical
    0.69
     identically
    0.67
     frustrated
    0.66
     antique
    0.66
     동일
    0.66
     exceeded
    0.66
     balcon
    0.66
    POSITIVE LOGITS
    -
    1.41
    ־
    1.08
    ‑
    0.93
    -}$
    0.87
    -]+
    0.86
    ـ
    0.86
    irme
    0.85
    [-]
    0.85
    mejor
    0.85
    -]
    0.84
    Act Density 0.015%

    No Known Activations