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
     목소
    -0.07
     chips
    -0.07
     PHPUnit
    -0.07
    Sur
    -0.06
    Azure
    -0.06
     laptop
    -0.06
    eurs
    -0.06
    abb
    -0.06
    Hamilton
    -0.06
    عي
    -0.06
    POSITIVE LOGITS
    >Welcome
    0.08
    ��
    0.06
    -master
    0.06
    subplot
    0.06
    idi
    0.06
    (pointer
    0.06
    entions
    0.06
    iyim
    0.06
    .flatMap
    0.06
    activities
    0.06
    Act Density 0.032%

    No Known Activations