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

    Neuronpedia

    INDEX
    Explanations

    decimal return rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maksymal
    0.42
    ě
    0.41
     корпус
    0.40
     вс
    0.39
     linseed
    0.39
    瑢
    0.38
    elerde
    0.37
    邾
    0.37
     দক্ষিণ
    0.36
    લ્
    0.36
    POSITIVE LOGITS
     sosok
    0.46
    Submission
    0.42
     aimé
    0.38
    땠
    0.38
     transcendent
    0.38
     managerial
    0.38
     कैसा
    0.37
    vived
    0.37
    Descending
    0.37
    ចែកចាយ
    0.37
    Act Density 0.008%

    No Known Activations