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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sono
    -0.07
     Manga
    -0.07
    <S
    -0.07
     cakes
    -0.06
     largely
    -0.06
    '',
    -0.06
     Question
    -0.06
    ncoder
    -0.06
    .getIn
    -0.06
    <H
    -0.06
    POSITIVE LOGITS
    .hw
    0.07
    Found
    0.07
    !!!↵↵
    0.06
    ooks
    0.06
    .ToInt
    0.06
    glfw
    0.06
    ражд
    0.06
     Тому
    0.06
    .rx
    0.06
    rodu
    0.06
    Act Density 0.021%

    No Known Activations