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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缸æ¯Ķä¹ĭä¸ĭ
    -0.32
    å½±éĻ¢
    -0.27
    igos
    -0.27
    ä¸Ģæĸ¹
    -0.27
    markt
    -0.26
    enticated
    -0.26
    /pub
    -0.25
    缸è¾ĥ
    -0.25
    åľ¨å½ĵåľ°
    -0.25
    vide
    -0.25
    POSITIVE LOGITS
    导èĪª
    0.31
    ses
    0.28
    SES
    0.25
     ÅĽc
    0.25
    ience
    0.24
    ije
    0.24
    apia
    0.24
    aping
    0.24
     kü
    0.24
     <<=
    0.24
    Act Density 0.079%

    No Known Activations