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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kg
    0.72
     capillaries
    0.70
    rah
    0.68
     Plessis
    0.65
     آمد
    0.65
     доб
    0.63
    ành
    0.61
    സ്ത്ര
    0.61
     kg
    0.60
    AY
    0.60
    POSITIVE LOGITS
    ળા
    0.75
    onske
    0.70
     Eltern
    0.69
    漪
    0.68
    চিব
    0.67
    valueChanged
    0.66
    ﻅ
    0.64
     зат
    0.63
    IMATE
    0.62
     Laufe
    0.61
    Act Density 0.068%

    No Known Activations