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

    Neuronpedia

    INDEX
    Explanations

    blog/article text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fade
    -0.07
    utations
    -0.07
    GX
    -0.07
     Naughty
    -0.06
    ["$
    -0.06
    σεις
    -0.06
    IDAD
    -0.06
     nutshell
    -0.06
    EEEE
    -0.06
    Fold
    -0.06
    POSITIVE LOGITS
    descriptor
    0.07
     FontWeight
    0.07
     disputed
    0.06
    etur
    0.06
     phát
    0.06
    Import
    0.06
     cheek
    0.06
    ステ
    0.06
    =cut
    0.06
    -ts
    0.06
    Act Density 0.070%

    No Known Activations