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

    Neuronpedia

    INDEX
    Explanations

    capitalized characters that could be a person's initials, potentially followed by a family name

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.60
    makeConstraints
    -0.54
    ęk
    -0.49
    ﷺ
    -0.48
     nhiêu
    -0.48
     AssemblyCulture
    -0.48
    principalTable
    -0.47
    ConstraintMaker
    -0.47
     FontFamily
    -0.46
     Permalink
    -0.46
    POSITIVE LOGITS
    δρο
    0.51
    ​—
    0.50
    gående
    0.50
    Jîn
    0.49
    PERTIES
    0.49
    uracy
    0.49
    Ос
    0.48
     EconPapers
    0.48
     GPT
    0.47
    ourite
    0.47
    Act Density 0.839%

    No Known Activations