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

    Neuronpedia

    INDEX
    Explanations

    Sure thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    presumably
    1.29
    로
    1.27
    ४
    1.19
    ная
    1.19
     ст
    1.18
    ik
    1.17
    PFA
    1.13
    і
    1.12
    ﮏ
    1.12
    其實
    1.11
    POSITIVE LOGITS
    तमंद
    2.17
     chắn
    2.02
    footed
    1.79
    પણે
    1.62
    likle
    1.49
    tte
    1.49
     weten
    1.47
    ll
    1.40
    ty
    1.39
     glad
    1.37
    Act Density 0.031%

    No Known Activations