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

    Neuronpedia

    INDEX
    Explanations

    Korean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Devil
    -0.07
    ML
    -0.07
     victory
    -0.07
     va
    -0.06
     neutral
    -0.06
    尽
    -0.06
     XL
    -0.06
     Nicola
    -0.06
    LA
    -0.06
    tpl
    -0.06
    POSITIVE LOGITS
    ang
    0.20
    ANG
    0.15
    ung
    0.15
    ong
    0.14
    eng
    0.13
    ONG
    0.13
     Bang
    0.13
     Kang
    0.12
     Sang
    0.12
    نگ
    0.12
    Act Density 0.125%

    No Known Activations