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

    Neuronpedia

    INDEX
    Explanations

    ranking options or methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    While
    1.22
    Furthermore
    1.14
    It
    1.13
    Its
    1.11
        
    1.07
    However
    1.05
    ↵↵
    1.01
       
    1.01
    There
    1.01
    Although
    0.97
    POSITIVE LOGITS
     please
    1.00
     no
    0.98
     \&
    0.98
     let
    0.90
     including
    0.90
     '
    0.89
     see
    0.88
     make
    0.87
     sorry
    0.87
     bitte
    0.87
    Act Density 0.441%

    No Known Activations