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

    Neuronpedia

    INDEX
    Explanations

    Work and you (scheduling)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tensor
    -0.07
    _unc
    -0.07
    inee
    -0.07
    (base
    -0.06
    (_("
    -0.06
    굣
    -0.06
    즌
    -0.06
     ش
    -0.06
    =<
    -0.06
    getKey
    -0.06
    POSITIVE LOGITS
     반
    0.07
    風格
    0.07
    orra
    0.07
     Colombia
    0.07
     Cah
    0.07
     timetable
    0.06
     weit
    0.06
    рог
    0.06
    @endif
    0.06
    ORG
    0.06
    Act Density 0.008%

    No Known Activations