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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doÄŁru
    -0.28
    .wx
    -0.28
    affles
    -0.26
    atform
    -0.26
    TMP
    -0.25
    =pos
    -0.24
    иÑĦика
    -0.24
    æ´¾
    -0.24
     Burgess
    -0.24
    æݬ
    -0.24
    POSITIVE LOGITS
    èĬ±å¼Ģ
    0.28
    çijĻ
    0.27
    éĿĴæµ·
    0.26
    篱
    0.25
    åѤç«ĭ
    0.25
    contained
    0.25
    æ¯įæł¡
    0.24
    尽快
    0.24
     pes
    0.24
     following
    0.24
    Act Density 0.054%

    No Known Activations