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

    Neuronpedia

    INDEX
    Explanations

    Starts a quote with question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æ±Ĥ
    -0.27
    ple
    -0.26
    å¢Ł
    -0.25
     chewing
    -0.25
    洪水
    -0.25
    èľī
    -0.24
    asions
    -0.24
     times
    -0.24
    (Table
    -0.24
    eb
    -0.23
    POSITIVE LOGITS
    rote
    0.28
    trade
    0.26
    anke
    0.25
    ScreenState
    0.25
    éĺħ读åħ¨æĸĩ
    0.24
    **/↵↵
    0.24
     gren
    0.24
    äº¬ä¸ľ
    0.24
    Amazon
    0.24
     Qué
    0.24
    Act Density 0.274%

    No Known Activations