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

    Neuronpedia

    INDEX
    Explanations

    listing variations or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.39
    0.37
    （
    0.35
    (\
    0.33
    '
    0.33
     (~
    0.32
    (
    0.31
     represents
    0.30
     ("
    0.30
     (\
    0.29
    POSITIVE LOGITS
     etcétera
    0.46
     тоже
    0.42
     whatnot
    0.40
    等等
    0.39
     وغیرہ
    0.38
     exponentes
    0.38
     वगैरह
    0.38
    也好
    0.36
     тощо
    0.36
     yaşanan
    0.35
    Act Density 0.126%

    No Known Activations