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
    <WebElement
    -0.07
    my
    -0.06
     handmade
    -0.06
    -${
    -0.06
     Fi
    -0.06
    δί
    -0.06
     serious
    -0.06
    گانی
    -0.06
    gars
    -0.06
    koli
    -0.06
    POSITIVE LOGITS
    (enc
    0.07
    =========↵
    0.06
    'ét
    0.06
    weapons
    0.06
    _Syntax
    0.06
    การแข
    0.06
     smr
    0.06
    }))↵↵
    0.06
    elerini
    0.06
     conson
    0.06
    Act Density 0.011%

    No Known Activations