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

    Neuronpedia

    INDEX
    Explanations

    coding style/structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SOC
    -0.09
    -story
    -0.08
     SOC
    -0.08
     psychic
    -0.08
     Antarctica
    -0.08
    ក្រ
    -0.07
     WTF
    -0.07
     бухгалтер
    -0.07
     किस
    -0.07
     struggle
    -0.07
    POSITIVE LOGITS
    0.09
     clarification
    0.07
     kullanıl
    0.07
    uak
    0.07
    详
    0.07
    Inherited
    0.07
    .touch
    0.07
    gült
    0.07
    Convertible
    0.07
    栏
    0.07
    Act Density 0.027%
    No Known Activations