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

    Neuronpedia

    INDEX
    Explanations

    after wards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ultimately
    0.38
    resc
    0.37
    uten
    0.36
    Result
    0.36
    <>
    0.36
    available
    0.36
     چاہتے
    0.35
    ’
    0.35
    Ultimately
    0.35
     لديها
    0.34
    POSITIVE LOGITS
    wards
    1.07
    WARDS
    0.90
    ward
    0.85
    noons
    0.84
     completing
    0.78
    thoughts
    0.76
     wards
    0.75
    math
    0.72
    WARD
    0.70
    words
    0.69
    Act Density 0.039%

    No Known Activations