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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    equals
    -0.07
    .emplace
    -0.06
     dalle
    -0.06
     js
    -0.06
     nemoc
    -0.06
     Schneider
    -0.06
     resistance
    -0.06
     uniform
    -0.06
     jokes
    -0.05
     جم
    -0.05
    POSITIVE LOGITS
     Mayo
    0.08
     GLint
    0.07
    и
    0.07
     Cecil
    0.07
     Industry
    0.07
    athy
    0.07
    FIG
    0.07
    ogra
    0.06
    itr
    0.06
    .Formatting
    0.06
    Act Density 0.016%

    No Known Activations