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

    Neuronpedia

    INDEX
    Explanations

    listing cons vs pros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conseguir
    2.48
     saada
    2.43
    categorie
    2.35
     accountability
    2.01
    বাবুর
    1.96
    inference
    1.95
    야
    1.91
    ка
    1.90
    Semitism
    1.89
    gym
    1.88
    POSITIVE LOGITS
    ifornia
    2.56
    ی
    2.51
     PartialEq
    2.25
    maßnahmen
    2.22
     QtGui
    2.14
     neph
    2.13
    셉
    2.10
    spiracy
    2.09
    inued
    2.09
     Jeremiah
    2.08
    Act Density 0.572%

    No Known Activations