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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handheld
    -0.08
    verte
    -0.08
     juvenile
    -0.08
    [rand
    -0.07
     olive
    -0.07
    )])
    -0.07
    餐
    -0.07
     verte
    -0.07
    odox
    -0.07
     sand
    -0.07
    POSITIVE LOGITS
     استخراج
    0.09
     extracted
    0.09
     获取
    0.08
     সংগ্র
    0.08
     Retrieve
    0.08
     progn
    0.08
    .extract
    0.07
     extraction
    0.07
     elemental
    0.07
     proxies
    0.07
    Act Density 0.023%

    No Known Activations