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

    Neuronpedia

    INDEX
    Explanations

    isomers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ethn
    -0.08
     పెట్ట
    -0.08
     garment
    -0.07
     Egypt
    -0.07
    .backward
    -0.07
     చేస
    -0.07
    ban
    -0.07
     griev
    -0.07
     humanities
    -0.07
     Osman
    -0.07
    POSITIVE LOGITS
    variants
    0.12
     variants
    0.11
     versions
    0.10
    /version
    0.09
    版本
    0.09
     Varianten
    0.09
     variant
    0.09
     Variant
    0.09
    (version
    0.09
    Variants
    0.08
    Act Density 0.013%

    No Known Activations