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

    Neuronpedia

    INDEX
    Explanations

    Dialogue punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subtract
    -0.08
     also
    -0.07
     أيضًا
    -0.07
     schn
    -0.07
    misc
    -0.07
     також
    -0.07
     také
    -0.07
     annon
    -0.07
     também
    -0.07
     arbitr
    -0.07
    POSITIVE LOGITS
     intrigued
    0.10
     incred
    0.10
     bewilder
    0.10
     বুঝ
    0.09
     fascinated
    0.09
    irling
    0.09
     stunned
    0.09
     unfamiliar
    0.09
    овер
    0.09
     fiquei
    0.09
    Act Density 0.042%

    No Known Activations