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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     frictional
    0.71
     automaton
    0.68
     stiffness
    0.65
     fruition
    0.63
     formality
    0.63
    テナンス
    0.63
    smanship
    0.62
     skepticism
    0.61
     Newtonian
    0.61
     aesthetic
    0.61
    POSITIVE LOGITS
    ва
    0.64
     refugi
    0.64
    𝖎
    0.64
    ᴅ
    0.63
     afirmou
    0.63
     PROTE
    0.61
    ﺭ
    0.61
    as
    0.61
     вида
    0.60
    👮
    0.59
    Act Density 1.520%

    No Known Activations