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

    Neuronpedia

    INDEX
    Explanations

    's or is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _a
    -0.07
    HA
    -0.06
     эти
    -0.06
    افه
    -0.06
    \t
    -0.06
     destiny
    -0.06
    _R
    -0.06
    UBLIC
    -0.06
     Nes
    -0.06
    ß
    -0.06
    POSITIVE LOGITS
     Newest
    0.07
     banda
    0.06
     Klo
    0.06
     ตำ
    0.06
     風
    0.06
     انتقال
    0.06
    (changes
    0.06
    .generated
    0.06
     ولی
    0.06
     นาง
    0.06
    Act Density 0.003%

    No Known Activations