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

    Neuronpedia

    INDEX
    Explanations

    sed ending words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ãģĬãĤĬ
    -0.12
    AGEMENT
    -0.10
    iÄĻ
    -0.10
    orado
    -0.09
    gerald
    -0.09
    dorf
    -0.09
    Äįer
    -0.09
    ียà¸Ķ
    -0.09
    erk
    -0.09
    ferred
    -0.09
    POSITIVE LOGITS
     sed
    0.17
    ation
    0.16
     Sed
    0.16
    iments
    0.14
    uction
    0.14
    iment
    0.14
    ition
    0.13
    angkan
    0.12
    ereal
    0.12
    ikit
    0.12
    Act Density 0.020%

    No Known Activations