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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rush
    -0.07
    .St
    -0.06
    Ch
    -0.06
    Svc
    -0.06
     mg
    -0.06
    RW
    -0.06
     Ple
    -0.06
     dcc
    -0.06
    組
    -0.06
     scept
    -0.06
    POSITIVE LOGITS
    Cop
    0.07
     hepsi
    0.07
    onedDateTime
    0.06
    テレビ
    0.06
     (...)
    0.06
     :::
    0.06
     ['.
    0.06
    ，其中
    0.06
     Piper
    0.06
    Ada
    0.06
    Act Density 0.005%

    No Known Activations