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

    Neuronpedia

    INDEX
    Explanations

    Sheets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atisfied
    -0.08
    quir
    -0.08
    ple
    -0.07
    models
    -0.07
    .SE
    -0.07
     getUserId
    -0.07
    "To
    -0.06
     млн
    -0.06
    www
    -0.06
    ποίηση
    -0.06
    POSITIVE LOGITS
    厚
    0.07
     Sty
    0.06
     paint
    0.06
     Shank
    0.06
     Leban
    0.06
     Sheet
    0.06
    *S
    0.06
    里面
    0.06
    แค
    0.06
     carte
    0.06
    Act Density 0.003%

    No Known Activations