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

    Neuronpedia

    INDEX
    Explanations

    select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cor
    -0.06
     Fab
    -0.06
    شت
    -0.06
    比利
    -0.06
    NBC
    -0.06
    Cel
    -0.06
    olkien
    -0.06
     Cohen
    -0.06
     Cap
    -0.06
    Jon
    -0.06
    POSITIVE LOGITS
    总是
    0.08
    irebase
    0.07
    ﯶ
    0.07
    杀
    0.07
    хран
    0.07
    -uppercase
    0.07
     Slider
    0.07
    .RunWith
    0.07
    /set
    0.07
     internal
    0.06
    Act Density 0.058%

    No Known Activations