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

    Neuronpedia

    INDEX
    Explanations

    function call or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েল
    0.74
    هههه
    0.74
     rocked
    0.73
    ে
    0.73
     hikes
    0.72
     breezes
    0.72
     sobriety
    0.71
    0.71
    opathic
    0.70
    ствие
    0.69
    POSITIVE LOGITS
    ない
    0.86
    sourceforge
    0.85
    皞
    0.84
     対象
    0.83
    စိတ်အပိုင်း
    0.82
    渫
    0.80
    あるいは
    0.80
    𝗘
    0.79
    fail
    0.79
     バル
    0.79
    Act Density 0.000%

    No Known Activations