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

    Neuronpedia

    INDEX
    Explanations

    avoid awkwardness and threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ❎
    0.48
    ↙
    0.38
    াসেব
    0.38
     hatched
    0.38
     citrus
    0.37
     benzyl
    0.37
     وسلم
    0.37
     twinkling
    0.37
     eddies
    0.36
     addicts
    0.36
    POSITIVE LOGITS
    ements
    0.40
    ലാ
    0.40
    liqu
    0.39
    बंद
    0.39
     US
    0.39
    sning
    0.39
     Liberty
    0.38
    ière
    0.38
    duh
    0.38
    US
    0.37
    Act Density 0.001%

    No Known Activations