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

    Neuronpedia

    INDEX
    Explanations

    code, math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itious
    -0.07
    NX
    -0.07
    十三
    -0.06
     █
    -0.06
    ducation
    -0.06
    現在
    -0.06
    佛
    -0.06
    �력
    -0.06
    गर
    -0.06
     مشتر
    -0.06
    POSITIVE LOGITS
    ál
    0.08
     đài
    0.07
    .ini
    0.07
     закін
    0.07
    appeared
    0.07
     Half
    0.07
    (coeffs
    0.06
     exceeding
    0.06
    all
    0.06
    Modifiers
    0.06
    Act Density 0.000%

    No Known Activations