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

    Neuronpedia

    INDEX
    Explanations

    stable bonds, fertility, policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘁
    0.47
    ка
    0.46
    }=
    0.45
    opening
    0.45
    adı
    0.45
    ர
    0.45
    opened
    0.44
    ту
    0.44
    wrote
    0.44
    ד
    0.44
    POSITIVE LOGITS
     sacraments
    0.48
     affidavits
    0.47
    '
    0.45
     scholarships
    0.43
     guidelines
    0.42
     fellowships
    0.41
     policies
    0.41
     foods
    0.40
    ؤول
    0.40
     literals
    0.40
    Act Density 0.004%

    No Known Activations