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

    Neuronpedia

    INDEX
    Explanations

    web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    代çIJĨ
    -0.28
     Pap
    -0.27
     pap
    -0.27
     Papers
    -0.26
    ä»ĭ
    -0.26
    empor
    -0.25
    åIJij举
    -0.25
    ä¸ĬæĿ¥
    -0.25
    éĢIJ
    -0.25
     properties
    -0.24
    POSITIVE LOGITS
    tps
    0.27
     derog
    0.27
    legs
    0.26
     smo
    0.25
    Ĩµ
    0.25
    ç¢Ł
    0.25
    è·Łå¥¹
    0.25
    åĤį
    0.24
    è¿ĻåIJį
    0.24
    drs
    0.24
    Act Density 0.027%

    No Known Activations