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

    Neuronpedia

    INDEX
    Explanations

    course

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أحمد
    -0.07
    -at
    -0.06
     Gill
    -0.06
    ニﾆ
    -0.06
    없음
    -0.06
     résultats
    -0.06
    ok
    -0.06
    larınızı
    -0.06
     HOLDER
    -0.06
     restored
    -0.06
    POSITIVE LOGITS
    predicted
    0.06
    Oops
    0.06
    _paper
    0.06
    clc
    0.06
     overwhelmed
    0.06
    /swagger
    0.06
     weaken
    0.06
    ‪
    0.06
     PARTIC
    0.06
     DELETE
    0.06
    Act Density 0.053%

    No Known Activations