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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    1.46
    л
    1.15
    н
    1.11
    o
    1.07
    т
    1.02
    담
    0.96
    sick
    0.95
    outputPath
    0.94
    omonas
    0.94
    у
    0.93
    POSITIVE LOGITS
    beli
    1.22
    hers
    1.19
    雩
    1.15
     adolescente
    1.15
    bells
    1.14
    Advert
    1.14
    लेले
    1.14
     Productions
    1.14
    িন
    1.13
     liberty
    1.12
    Act Density 0.000%

    No Known Activations