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

    Neuronpedia

    INDEX
    Explanations

    . / , / by / to / are / is / ues / asing / available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ר
    1.39
    er
    1.15
    ти
    1.14
    ر
    1.13
    తో
    1.12
    ০
    1.11
    使用
    1.10
    র
    1.10
    ות
    1.09
    ช่วง
    1.09
    POSITIVE LOGITS
    ьте
    1.27
    getVisibility
    1.08
    ری
    1.05
     convexe
    1.02
     isole
    0.99
     οποία
    0.98
     arrondie
    0.97
     remer
    0.97
     infest
    0.93
     incend
    0.92
    Act Density 0.047%

    No Known Activations