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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sauvages
    -0.56
     levure
    -0.50
     vestiti
    -0.49
     skär
    -0.47
     yelek
    -0.46
     rör
    -0.46
     présidenti
    -0.46
     vostri
    -0.45
     colorés
    -0.45
     loisirs
    -0.45
    POSITIVE LOGITS
     صوتيه
    0.65
    AccessorTable
    0.62
     hairpin
    0.61
    exitRule
    0.59
    DockStyle
    0.57
     Hez
    0.57
     distraction
    0.54
    الدراسه
    0.54
     profile
    0.52
    IsContent
    0.52
    Act Density 0.002%

    No Known Activations