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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Support
    -0.07
    Número
    -0.07
    kání
    -0.07
     Buffalo
    -0.07
    Av
    -0.06
     Doctrine
    -0.06
     Analyst
    -0.06
     glacier
    -0.06
    /ion
    -0.06
    /")↵
    -0.06
    POSITIVE LOGITS
    acey
    0.06
    ods
    0.06
    ीड
    0.06
    weeney
    0.06
    yyval
    0.06
     army
    0.06
    您的
    0.06
    이다
    0.06
     چرا
    0.05
     wondered
    0.05
    Act Density 0.015%

    No Known Activations