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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خواهند
    -0.07
    Destroy
    -0.06
    ensi
    -0.06
    undles
    -0.06
    说
    -0.06
    Hyper
    -0.06
     titul
    -0.06
    inp
    -0.06
     Sit
    -0.06
    -0.06
    POSITIVE LOGITS
     knit
    0.07
     Foundations
    0.07
     scientists
    0.06
     Gene
    0.06
     VIII
    0.06
    -pad
    0.06
    gota
    0.06
    τουργ
    0.06
     hysteria
    0.06
    -floating
    0.06
    Act Density 0.031%

    No Known Activations