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

    Neuronpedia

    INDEX
    Explanations

    source code and licensing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çݰ代åĮĸ
    -0.26
    è¶ħé«ĺ
    -0.26
     обÑĢазом
    -0.25
    æ¯ı个人çļĦ
    -0.25
    æĮ¥æīĭ
    -0.24
    ä¸Ŀ
    -0.24
    è¿ľç¨ĭ
    -0.24
    quit
    -0.24
    auc
    -0.24
    à¹Ħà¸ģล
    -0.24
    POSITIVE LOGITS
     also
    0.28
    éĻ¤å¤ĸ
    0.27
     belongs
    0.26
     mind
    0.25
     will
    0.25
    коÑĢ
    0.25
     corros
    0.25
    angen
    0.24
     blo
    0.24
     first
    0.23
    Act Density 0.009%

    No Known Activations