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

    Neuronpedia

    INDEX
    Explanations

    `__FILE__` or related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Вайлдберриз
    0.42
     unanswered
    0.39
    éseket
    0.39
    avasena
    0.39
    嶆
    0.38
     खास
    0.38
    óle
    0.38
    紫外線
    0.37
    BlockFit
    0.37
    সংখ্যা
    0.36
    POSITIVE LOGITS
    гни
    0.41
     tand
    0.41
     teg
    0.38
     Edison
    0.38
     contend
    0.37
     reflect
    0.37
     trol
    0.36
     tuba
    0.36
     said
    0.36
    tin
    0.36
    Act Density 0.000%

    No Known Activations