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

    Neuronpedia

    INDEX
    Explanations

    earrings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhe
    -0.08
     tokenizer
    -0.08
     winding
    -0.07
    urable
    -0.07
     elasticity
    -0.07
     rigidity
    -0.07
     stiffness
    -0.07
    urende
    -0.07
    jours
    -0.07
    299
    -0.07
    POSITIVE LOGITS
     earrings
    0.12
     Earrings
    0.10
     രണ്ടു
    0.09
     দুটি
    0.08
     Ам
    0.08
     одно
    0.08
     patt
    0.08
    usuf
    0.08
     രണ്ട്
    0.08
     dois
    0.08
    Act Density 0.003%

    No Known Activations