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

    Neuronpedia

    INDEX
    Explanations

    Beyond VR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    antam
    0.44
    encing
    0.44
    ouncing
    0.43
    arent
    0.42
    ation
    0.42
    ised
    0.40
    dale
    0.40
     allevi
    0.39
     fruition
    0.39
     physically
    0.39
    POSITIVE LOGITS
     平
    0.44
    プレミアム
    0.43
    ように
    0.43
    臻
    0.43
    最高の
    0.42
    拣
    0.42
     Supremo
    0.42
    大
    0.42
    暂
    0.42
    b
    0.41
    Act Density 0.003%

    No Known Activations