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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by equals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jahter
    0.46
    -{\
    0.43
    শাস
    0.42
    ])));
    0.42
     ಶ್ರೀ
    0.42
    াৰ
    0.42
    }&\
    0.42
    },{"
    0.41
    |");
    0.41
     $\$
    0.41
    POSITIVE LOGITS
     =
    2.31
    =
    2.03
    ＝
    1.71
     equals
    1.55
     $=
    1.55
     =,
    1.54
    =\
    1.49
     $=$
    1.44
    }=
    1.42
    $=
    1.42
    Act Density 0.241%

    No Known Activations