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

    Neuronpedia

    INDEX
    Explanations

    Native tokens and their appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     look
    0.45
    Look
    0.42
     Look
    0.41
     looking
    0.36
    M
    0.36
    look
    0.36
     tr
    0.36
     نگاه
    0.35
     (
    0.35
    間
    0.35
    POSITIVE LOGITS
     erscheinen
    0.55
    appears
    0.54
     Appear
    0.53
     aparecer
    0.52
     erscheint
    0.52
     apparaissent
    0.52
     ظاهر
    0.52
     appears
    0.51
    詑
    0.51
     erschienen
    0.50
    Act Density 0.000%

    No Known Activations