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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XII
    -0.08
     spread
    -0.07
    沐
    -0.07
     Consultants
    -0.06
    .returnValue
    -0.06
    .Charting
    -0.06
     shoots
    -0.06
    _rq
    -0.06
    会同
    -0.06
    енную
    -0.06
    POSITIVE LOGITS
    onDelete
    0.07
    _SENS
    0.07
     '&#
    0.07
    義務
    0.07
    第一步
    0.07
    .En
    0.07
    田
    0.07
    (require
    0.07
    稼
    0.07
    defense
    0.07
    Act Density 0.035%

    No Known Activations