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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     대표
    -0.07
    라
    -0.07
    .console
    -0.06
    ()->
    -0.06
    ikan
    -0.06
    -metal
    -0.06
     disparities
    -0.06
     lent
    -0.06
    Š
    -0.06
     เล
    -0.06
    POSITIVE LOGITS
    oops
    0.07
    .month
    0.06
    <?>>
    0.06
     thoải
    0.06
    �
    0.06
     Jedi
    0.06
     Overflow
    0.06
     собою
    0.06
    .toJSONString
    0.06
    <!
    0.06
    Act Density 0.097%

    No Known Activations