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

    Neuronpedia

    INDEX
    Explanations

    offspring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ير
    1.15
    ismen
    1.09
    onomy
    1.08
    ようになりました
    1.04
    č
    1.04
    ani
    1.02
    okość
    1.02
    ület
    1.01
    arono
    1.01
    الك
    1.00
    POSITIVE LOGITS
     predecess
    1.12
     confus
    1.09
     conda
    1.06
    sixth
    1.06
     дале
    1.05
     siya
    1.03
     Initialize
    1.02
     joc
    1.02
    ים
    1.02
    ीत
    1.01
    Act Density 0.009%

    No Known Activations