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

    Neuronpedia

    INDEX
    Explanations

    objects, disease, freedom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зку
    0.43
     shouldUse
    0.39
     зре
    0.39
    дето
    0.38
    force
    0.38
    evenly
    0.38
    ඍ
    0.37
     conceito
    0.36
    recation
    0.36
    führen
    0.36
    POSITIVE LOGITS
     আহসান
    0.42
     została
    0.39
     whip
    0.38
     kho
    0.38
     Virgen
    0.38
    ွင်း
    0.37
     وتس
    0.37
     James
    0.36
     Khan
    0.36
     whipping
    0.36
    Act Density 0.000%

    No Known Activations