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

    Neuronpedia

    INDEX
    Explanations

    need to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”.
    0.99
    ​.
    0.98
    ™.
    0.97
    .”
    0.96
    *.
    0.92
     ».
    0.92
    ».
    0.89
    ".
    0.88
    '.
    0.87
     kyll
    0.86
    POSITIVE LOGITS
     एखा
    1.14
    ၊
    1.13
     autoWatch
    1.07
    ،
    1.07
     एखाद्या
    1.06
    íonn
    1.04
     گے
    1.03
     चाहें
    1.01
     linestyle
    1.00
     ہے
    0.99
    Act Density 0.646%

    No Known Activations