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

    Neuronpedia

    INDEX
    Explanations

    phrases for summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    起身
    1.38
    轳
    1.36
    onics
    1.35
    aholic
    1.34
    itech
    1.33
    orough
    1.32
    rimazole
    1.32
    ្ខ
    1.31
     ಅನುಪ
    1.29
     guilty
    1.28
    POSITIVE LOGITS
    In
    1.30
     In
    1.23
    Bon
    1.15
     Proposition
    1.14
    Especific
    1.12
     fixed
    1.12
    زی
    1.11
     forne
    1.10
     النها
    1.09
     Explicit
    1.09
    Act Density 0.019%

    No Known Activations