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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by st

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Responder
    1.29
     Environments
    1.23
     Drinking
    1.22
    ﾓ
    1.20
     Почему
    1.20
    λλά
    1.20
    ْر
    1.19
     Quantification
    1.18
     Covering
    1.18
     Чтобы
    1.17
    POSITIVE LOGITS
    cle
    1.25
    c
    1.16
    t
    1.12
    paid
    0.99
    p
    0.97
    ことは
    0.96
    class
    0.95
    cad
    0.95
    exhaust
    0.95
    sk
    0.94
    Act Density 0.080%

    No Known Activations