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

    Neuronpedia

    INDEX
    Explanations

    technical components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人
    0.48
    нул
    0.45
     устрой
    0.44
     privacidad
    0.44
    ociação
    0.43
    цы
    0.43
     opacity
    0.42
     You
    0.42
    t
    0.40
    位
    0.40
    POSITIVE LOGITS
     settimana
    0.52
     தேவை
    0.51
     THOMAS
    0.51
     منٹو
    0.49
     ब्रै
    0.48
     revising
    0.48
     DIFFIC
    0.48
     FACTORS
    0.48
     बस
    0.47
     เฮ
    0.47
    Act Density 0.001%

    No Known Activations