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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ester
    -0.07
     Server
    -0.06
     Ра
    -0.06
    FLICT
    -0.06
    xies
    -0.06
    ких
    -0.06
    .DropTable
    -0.06
     dari
    -0.06
    quette
    -0.06
     zs
    -0.06
    POSITIVE LOGITS
     uphol
    0.07
    ++);↵
    0.07
    .Rotate
    0.07
    嗯
    0.07
    extracomment
    0.06
    (match
    0.06
     punches
    0.06
    xFE
    0.06
    Rejected
    0.06
     det
    0.06
    Act Density 0.199%

    No Known Activations