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

    Neuronpedia

    INDEX
    Explanations

    python code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     następnie
    0.77
     অতঃপর
    0.75
    aws
    0.74
    Color
    0.73
    astien
    0.73
    AL
    0.73
     prawd
    0.72
    Aid
    0.72
    Auf
    0.71
    وَ
    0.71
    POSITIVE LOGITS
     banning
    0.71
     avoided
    0.70
    ierge
    0.65
    ificante
    0.64
     avoiding
    0.63
    ↵↵
    0.61
     scratched
    0.60
     preventing
    0.60
     outraged
    0.59
    ➣
    0.59
    Act Density 0.045%

    No Known Activations