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

    Neuronpedia

    INDEX
    Explanations

    start bearing computer specialist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அடைய
    0.46
     हमेशा
    0.42
     Always
    0.42
     உதவிய
    0.42
     மற்றும்
    0.41
     वाले
    0.41
     பக்த
    0.41
    자와
    0.41
     أيضا
    0.40
     և
    0.40
    POSITIVE LOGITS
    ⸨
    0.53
    ριά
    0.43
     bzw
    0.43
    ᾰ
    0.43
    ﭑ
    0.42
     stint
    0.42
    .*;
    0.40
    Segue
    0.40
     instalments
    0.40
     mortgages
    0.40
    Act Density 0.309%

    No Known Activations