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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anager
    -0.26
    erring
    -0.25
    KeyType
    -0.24
    atable
    -0.24
    istringstream
    -0.24
     listed
    -0.24
    apa
    -0.24
    人éĢł
    -0.24
     Cardinal
    -0.24
    åIJı
    -0.23
    POSITIVE LOGITS
    kommen
    0.27
    lush
    0.27
     Omn
    0.27
    å½ĵäºĭ
    0.26
     Hay
    0.25
    ten
    0.25
    åĩłå¼ł
    0.25
    men
    0.25
    æ´¾
    0.24
    洪水
    0.24
    Act Density 0.001%

    No Known Activations