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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WH
    -0.06
     MHz
    -0.06
     volleyball
    -0.06
     Minds
    -0.06
     Weber
    -0.06
     straně
    -0.06
     IMD
    -0.06
    hd
    -0.06
     Wag
    -0.06
    292
    -0.06
    POSITIVE LOGITS
    .addAction
    0.07
    enumer
    0.07
     setBackgroundImage
    0.07
    _LOGIN
    0.06
    ./(
    0.06
     już
    0.06
     düzenlem
    0.06
    =?",
    0.06
    _patterns
    0.06
    intel
    0.06
    Act Density 0.091%

    No Known Activations