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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inus
    -0.06
    eh
    -0.06
    بال
    -0.06
     kteří
    -0.06
    esus
    -0.06
    نا
    -0.06
     �
    -0.06
     '/'
    -0.05
     να
    -0.05
     producto
    -0.05
    POSITIVE LOGITS
    memiş
    0.07
    ocom
    0.07
    �
    0.07
    InParameter
    0.07
     unintended
    0.07
    embali
    0.07
     withholding
    0.06
     wholes
    0.06
    mazon
    0.06
     sponge
    0.06
    Act Density 0.008%

    No Known Activations