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

    Neuronpedia

    INDEX
    Explanations

    allowed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __)↵
    -0.07
     en
    -0.06
    #$
    -0.06
    .One
    -0.06
    ovní
    -0.06
     Kostenlose
    -0.06
    _Manager
    -0.06
     enqueue
    -0.06
    ола
    -0.06
    iyel
    -0.06
    POSITIVE LOGITS
    hou
    0.07
     Doub
    0.06
    λλην
    0.06
    omik
    0.06
    ágina
    0.06
    ully
    0.05
     Aberdeen
    0.05
     Comics
    0.05
    够
    0.05
    (tile
    0.05
    Act Density 0.038%

    No Known Activations