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

    Neuronpedia

    INDEX
    Explanations

    code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensch
    -0.07
    ...');↵
    -0.07
    ाम
    -0.07
     दस
    -0.07
    '])){
    -0.07
    etty
    -0.07
     mf
    -0.06
    。那
    -0.06
    onium
    -0.06
     comunidad
    -0.06
    POSITIVE LOGITS
    Limited
    0.07
    agues
    0.06
    -complete
    0.06
    regon
    0.06
    opl
    0.06
    684
    0.06
     баж
    0.06
     Ply
    0.06
     Unsure
    0.06
    λου
    0.06
    Act Density 0.000%

    No Known Activations