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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    图片
    -0.07
    gebn
    -0.06
    енный
    -0.06
    loon
    -0.06
    without
    -0.06
    ků
    -0.06
     pie
    -0.06
    шую
    -0.06
    _();↵
    -0.06
     vyšší
    -0.06
    POSITIVE LOGITS
    (stypy
    0.07
    'une
    0.07
    �
    0.07
     RSS
    0.06
    AllArgsConstructor
    0.06
     δύο
    0.06
     цент
    0.06
    AndUpdate
    0.06
    τέ
    0.06
    xml
    0.06
    Act Density 0.001%

    No Known Activations