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

    Neuronpedia

    INDEX
    Explanations

    phrasal verbs and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.21
     iterating
    0.20
     timestep
    0.20
    ）：
    0.20
     were
    0.20
     هستند
    0.19
    都
    0.19
     باستخدام
    0.19
    អំ
    0.18
     عندما
    0.18
    POSITIVE LOGITS
     us
    0.19
    了不少
    0.18
     собою
    0.18
     swój
    0.17
    自己的
    0.17
    il
    0.17
     dirinya
    0.17
    αρ
    0.16
    iddag
    0.16
    更多的
    0.15
    Act Density 0.652%

    No Known Activations