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

    Neuronpedia

    INDEX
    Explanations

    line breaks and spacing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LGBTQ
    0.78
     mosa
    0.75
     Realms
    0.72
     rebranded
    0.72
     lossless
    0.72
     Metaverse
    0.71
     DNS
    0.71
     TypeScript
    0.70
     wielding
    0.69
     лежа
    0.69
    POSITIVE LOGITS
    indent
    1.20
    Indent
    1.11
    width
    1.09
     indent
    1.04
    Width
    1.00
    height
    0.98
     width
    0.97
    Spacing
    0.91
    环境
    0.91
    sep
    0.89
    Act Density 0.044%

    No Known Activations