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

    Neuronpedia

    INDEX
    Explanations

    code, data, text structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pam
    0.38
    Brid
    0.38
     chale
    0.38
    ႉ
    0.37
     fortr
    0.37
    摻
    0.37
    Thi
    0.36
    Pam
    0.36
    ^{[
    0.36
     **,
    0.35
    POSITIVE LOGITS
     boxes
    0.38
    boxes
    0.38
     autonomy
    0.38
     losers
    0.38
    alyse
    0.37
    দয়
    0.37
     contractual
    0.36
    отно
    0.36
     الوقت
    0.36
    нні
    0.36
    Act Density 0.000%

    No Known Activations