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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     상당히
    0.30
     complicada
    0.29
     bruta
    0.29
     เต็ม
    0.28
     seinem
    0.28
     mancan
    0.28
     spermato
    0.27
     sadistic
    0.27
     sujet
    0.26
    appliqu
    0.26
    POSITIVE LOGITS
    id
    0.32
    list
    0.29
    M
    0.28
    for
    0.28
    类型
    0.27
    D
    0.27
    New
    0.27
    缺少
    0.27
    选项
    0.27
    List
    0.26
    Act Density 0.183%

    No Known Activations