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

    Neuronpedia

    INDEX
    Explanations

    text rotation and horizontal alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    labelText
    0.49
    asText
    0.49
     text
    0.48
     текст
    0.48
    myLabels
    0.47
     labeling
    0.47
     labelling
    0.46
    文字
    0.45
     primaryLanguage
    0.44
     labels
    0.42
    POSITIVE LOGITS
     rotation
    0.55
     Horizontal
    0.50
     horizontal
    0.49
     Rotation
    0.49
     ha
    0.49
     Ha
    0.48
    rotation
    0.46
     rotations
    0.44
    horizontal
    0.44
    Horizontal
    0.43
    Act Density 0.001%

    No Known Activations