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

    Neuronpedia

    INDEX
    Explanations

    Random text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sadece
    -0.07
     adipiscing
    -0.06
     ||
↵
    -0.06
    ]],
    -0.06
     Paren
    -0.06
     frail
    -0.06
     Frauen
    -0.06
     Göz
    -0.06
    ";↵↵
    -0.06
     noch
    -0.06
    POSITIVE LOGITS
    474
    0.07
    486
    0.07
    _register
    0.06
    ----
    0.06
    _GAIN
    0.06
     Symbols
    0.06
    473
    0.06
     ＜
    0.06
     brochure
    0.06
     CBS
    0.06
    Act Density 0.127%

    No Known Activations