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

    Neuronpedia

    INDEX
    Explanations

    XML file parsing and editing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kotlinx
    0.89
    }/>
    0.89
    ⌥
    0.88
     worldRank
    0.86
    즌
    0.84
    britannien
    0.84
    ]));
    0.83
    ably
    0.82
     rebuke
    0.82
    forceable
    0.82
    POSITIVE LOGITS
    𝐚
    0.98
    સ
    0.97
    ো
    0.95
    س
    0.86
    म
    0.85
    Ве
    0.81
     escult
    0.79
    وت
    0.78
    fromRGBO
    0.77
    সু
    0.77
    Act Density 0.037%

    No Known Activations