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

    Neuronpedia

    INDEX
    Explanations

    everything

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uniform
    -0.07
     AFP
    -0.07
    xlsx
    -0.06
    mute
    -0.06
    ocrisy
    -0.06
    GLOBAL
    -0.06
     Якщо
    -0.06
     tipos
    -0.06
     Hancock
    -0.06
     Metropolitan
    -0.06
    POSITIVE LOGITS
     Malays
    0.06
    JS
    0.06
     DataAccess
    0.06
    ]);↵↵
    0.06
     elegance
    0.06
     잘
    0.06
    bo
    0.06
     Everything
    0.06
     Naj
    0.06
    bidden
    0.06
    Act Density 0.024%

    No Known Activations