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

    Neuronpedia

    INDEX
    Explanations

    defining function and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    अमेर
    0.48
    ﻁ
    0.48
    ﺀ
    0.46
     forbidding
    0.46
    કિસ્
    0.46
    țit
    0.45
     कीमत
    0.45
     ಸಾಕಷ್ಟು
    0.45
     составля
    0.45
    jš
    0.44
    POSITIVE LOGITS
     interview
    0.54
     workspaces
    0.45
    ing
    0.43
    换
    0.43
    {
    0.43
    :
    0.42
    interview
    0.41
    َ
    0.41
    workspace
    0.40
     musique
    0.40
    Act Density 0.002%

    No Known Activations