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

    Neuronpedia

    INDEX
    Explanations

    any treatment decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    logrus
    0.28
    boldsymbol
    0.28
    ISHING
    0.27
     dimensionless
    0.27
    oretically
    0.27
    oramic
    0.27
    влека
    0.26
     dichotomy
    0.26
    categorical
    0.26
     педагоги
    0.26
    POSITIVE LOGITS
     Behandlung
    0.36
     traitement
    0.35
     Treatment
    0.34
     치료
    0.33
     treatment
    0.33
    治疗
    0.33
     любом
    0.32
     अन्यथा
    0.31
     Don
    0.31
    Treatment
    0.31
    Act Density 0.014%

    No Known Activations