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

    Neuronpedia

    INDEX
    Explanations

    Information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rampant
    -0.08
     DISP
    -0.07
     Đông
    -0.07
     אם
    -0.07
     cav
    -0.07
     Dan
    -0.07
    城际
    -0.07
     StringUtils
    -0.07
    直流
    -0.06
    成语
    -0.06
    POSITIVE LOGITS
    -community
    0.07
    �
    0.07
    .Before
    0.07
    魉
    0.07
     Toastr
    0.06
    unteer
    0.06
    在过渡期
    0.06
    payer
    0.06
     oracle
    0.06
    *
    0.06
    Act Density 0.011%

    No Known Activations