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

    Neuronpedia

    INDEX
    Explanations

    explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Cache
    -0.07
     dễ
    -0.07
    ẳng
    -0.07
    军
    -0.06
    ovém
    -0.06
    _closed
    -0.06
    但
    -0.06
    疲
    -0.06
     своб
    -0.06
     Gupta
    -0.06
    POSITIVE LOGITS
     kel
    0.07
     biz
    0.06
    .labelX
    0.06
    aul
    0.06
     Erotic
    0.06
     quam
    0.06
     climates
    0.06
     termin
    0.06
     Tenn
    0.06
    ('{{
    0.05
    Act Density 0.194%

    No Known Activations