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

    Neuronpedia

    INDEX
    Explanations

    numerical data and scientific notation, especially with units of measurement

    oai_token-act-pair · gemini-2.0-flash

    forward slash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cans
    -0.88
    ths
    -0.88
    ONS
    -0.85
    hams
    -0.84
    tops
    -0.84
    ups
    -0.83
    asts
    -0.83
    dams
    -0.82
    cels
    -0.82
    rts
    -0.82
    POSITIVE LOGITS
     autorytatywna
    0.60
    Rhestr
    0.57
    ########.
    0.55
    yarnpkg
    0.48
    bootstrapcdn
    0.46
    contentLoaded
    0.46
     AssemblyCulture
    0.46
    WriteBarrier
    0.45
    twimg
    0.43
    hoeddwyd
    0.43
    Act Density 41.310%

    No Known Activations