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

    Neuronpedia

    INDEX
    Explanations

    world records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Therapy
    0.43
    Methods
    0.42
     therapy
    0.42
     Like
    0.40
     Attitudes
    0.38
    Works
    0.38
    Apps
    0.38
    Over
    0.38
    Like
    0.38
     Landscapes
    0.37
    POSITIVE LOGITS
    myLabels
    0.44
    ടെ
    0.41
     flanges
    0.41
    <unused2009>
    0.40
    routingHeader
    0.40
     malef
    0.40
     MiG
    0.39
    ismuth
    0.39
    oniazid
    0.39
     சரா
    0.39
    Act Density 0.008%

    No Known Activations