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

    Neuronpedia

    INDEX
    Explanations

    stroke width

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Strokes
    0.45
    Stroke
    0.42
    stroke
    0.41
     strokes
    0.41
     specialist
    0.41
    ClassName
    0.40
     Stroke
    0.40
     experts
    0.40
     Specials
    0.40
     Pilgr
    0.39
    POSITIVE LOGITS
     anchor
    0.52
    anchor
    0.46
    رمز
    0.43
     anchors
    0.42
    Anchor
    0.42
     Anchor
    0.41
    روح
    0.41
     delimited
    0.40
    蝓
    0.40
     Maugin
    0.39
    Act Density 0.001%

    No Known Activations