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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     சோ
    0.30
     लक्ष्य
    0.27
     fruto
    0.27
     ambito
    0.27
     இதில்
    0.26
     gerenci
    0.26
     подразуме
    0.26
     enormes
    0.26
     elementos
    0.25
     gestione
    0.25
    POSITIVE LOGITS
    0
    0.25
    ة
    0.25
    of
    0.24
     polls
    0.23
    ліся
    0.23
    <0xEB>
    0.23
    ication
    0.23
    לה
    0.23
    يله
    0.23
    ſ
    0.23
    Act Density 0.018%

    No Known Activations