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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ичні
    -0.06
    lista
    -0.06
    рави
    -0.06
    Sprites
    -0.06
     이전
    -0.06
    CB
    -0.06
     Ramirez
    -0.06
    romě
    -0.06
    ۱۳۹
    -0.06
    pherical
    -0.06
    POSITIVE LOGITS
     Janet
    0.07
    .authorization
    0.06
     몽
    0.06
     ({↵
    0.06
     forState
    0.06
    则
    0.06
    .Note
    0.06
     helped
    0.06
    .request
    0.06
    ";↵↵↵
    0.06
    Act Density 0.033%

    No Known Activations