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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .display
    -0.07
     Uk
    -0.06
    icity
    -0.06
    พน
    -0.06
    pan
    -0.06
    earth
    -0.06
    Domain
    -0.06
    .put
    -0.06
     tak
    -0.06
    Red
    -0.06
    POSITIVE LOGITS
    .getRuntime
    0.07
     على
    0.07
    hoa
    0.07
    атели
    0.06
     elusive
    0.06
     (--
    0.06
     frase
    0.06
    /loose
    0.06
    센터
    0.06
    .
↵
    0.06
    Act Density 0.002%

    No Known Activations