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

    Neuronpedia

    INDEX
    Explanations

    inference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.71
     ProtoMessage
    -0.69
     autorytatywna
    -0.69
     незавершена
    -0.64
     المعيارى
    -0.62
     distanciation
    -0.62
     defaultstate
    -0.61
     متعلقه
    -0.59
     intptr
    -0.58
    ⓧ
    -0.57
    POSITIVE LOGITS
    Dữ
    0.69
     ferner
    0.54
     Cached
    0.50
     PRS
    0.49
    Hear
    0.48
     HCI
    0.48
    preduce
    0.48
     MCQ
    0.47
     extrinsic
    0.47
     PCB
    0.47
    Act Density 0.135%

    No Known Activations