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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exit
    -0.34
    Exit
    -0.34
     exit
    -0.30
    .Exit
    -0.29
    rox
    -0.29
    ä¸įä¸ĭ
    -0.29
     Theory
    -0.27
    exit
    -0.26
    _exit
    -0.26
    à¦ī
    -0.25
    POSITIVE LOGITS
    约æĿŁ
    0.27
    åĽ½èµĦ
    0.25
    çĸij
    0.25
    cast
    0.25
    ä½ı
    0.25
    éĵº
    0.25
    idl
    0.25
    è¯ģåĪ¸æĬķèµĦ
    0.24
    ining
    0.24
    -tests
    0.24
    Act Density 1.341%

    No Known Activations