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

    Neuronpedia

    INDEX
    Explanations

    organized steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </sub>
    0.41
    скольку
    0.41
     וי
    0.41
     বলবে
    0.41
     aislamiento
    0.41
     保護
    0.41
    謂
    0.40
    awi
    0.40
     параметров
    0.39
     perteneciente
    0.39
    POSITIVE LOGITS
    游客
    0.44
    铁路
    0.43
    Critic
    0.43
     뜨
    0.42
    国际
    0.42
    节目
    0.42
     Anfield
    0.41
     Irish
    0.41
     चारा
    0.41
     Synod
    0.40
    Act Density 0.009%

    No Known Activations