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

    Neuronpedia

    INDEX
    Explanations

    workplace complaints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tx
    -0.07
    usal
    -0.07
    .API
    -0.06
     durations
    -0.06
     ListViewItem
    -0.06
    wand
    -0.06
    НА
    -0.06
    phies
    -0.06
     العظ
    -0.06
    ธน
    -0.06
    POSITIVE LOGITS
    mare
    0.07
    午
    0.07
    conditional
    0.06
     beside
    0.06
     Komm
    0.06
    аются
    0.06
     redu
    0.06
    _needed
    0.06
    ]<
    0.06
     recharge
    0.06
    Act Density 0.019%

    No Known Activations