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

    Neuronpedia

    INDEX
    Explanations

    academic and professional roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेंसेस
    0.35
    ientôt
    0.32
     primitives
    0.30
     جائیں
    0.29
     അയാൾ
    0.29
     anarchy
    0.29
     malice
    0.28
     latérales
    0.28
     nois
    0.28
     nudity
    0.28
    POSITIVE LOGITS
     professor
    0.67
     profesor
    0.54
    professor
    0.54
     Professor
    0.52
     director
    0.49
     emeritus
    0.49
     Director
    0.48
     educator
    0.48
     профессор
    0.48
     professeur
    0.47
    Act Density 0.043%

    No Known Activations