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

    Neuronpedia

    INDEX
    Explanations

    Instructions, steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    骎
    -0.07
     dungeon
    -0.07
     wan
    -0.07
    thinking
    -0.07
    �
    -0.06
    زين
    -0.06
     exam
    -0.06
    퀭
    -0.06
     SharePoint
    -0.06
    (property
    -0.06
    POSITIVE LOGITS
    ).</
    0.08
    .out
    0.08
    <Object
    0.07
    镉
    0.07
    chooser
    0.07
     нашей
    0.07
    =logging
    0.07
    )->
    0.07
    _rest
    0.07
    )").
    0.07
    Act Density 0.010%

    No Known Activations