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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hab
    -0.07
    bright
    -0.07
    xious
    -0.06
     Presentation
    -0.06
    -band
    -0.06
    毛
    -0.06
    MAC
    -0.06
    mey
    -0.06
     amplitude
    -0.06
    sheets
    -0.06
    POSITIVE LOGITS
    :");↵↵
    0.07
    "])
↵
    0.07
    ')");↵
    0.07
    قية
    0.07
    ']},↵
    0.07
    '});↵
    0.07
    ()
↵
↵
↵
    0.07
     takové
    0.07
    .’”↵↵
    0.07
    "));
↵
↵
    0.07
    Act Density 2.718%

    No Known Activations