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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ος
    -1.48
     تانيه
    -0.69
    الإنجليزية
    -0.68
     Efq
    -0.68
     typelib
    -0.62
     XCTest
    -0.60
    orianCalendar
    -0.60
    Seguir
    -0.59
    amental
    -0.59
     sauvages
    -0.59
    POSITIVE LOGITS
     gynhyrchwyd
    0.45
    kegaard
    0.45
    XDECREF
    0.44
    ত্র
    0.41
     كومونز
    0.41
    DrawerToggle
    0.39
     désolés
    0.39
     vaste
    0.39
     comuniques
    0.39
    ists
    0.38
    Act Density 0.127%

    No Known Activations