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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convenience
    -0.06
    SET
    -0.06
    .!
    -0.06
     intention
    -0.06
    cat
    -0.06
    )/
    -0.06
     favoured
    -0.06
     Higgins
    -0.06
    _pv
    -0.06
     OW
    -0.06
    POSITIVE LOGITS
    ylv
    0.07
    leDb
    0.07
     BITS
    0.07
     shootings
    0.07
    reh
    0.06
    reso
    0.06
    putc
    0.06
    capitalize
    0.06
    .charCodeAt
    0.06
    นค
    0.06
    Act Density 0.027%

    No Known Activations