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

    Neuronpedia

    INDEX
    Explanations

    online calculators and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உருவாக்கிய
    0.55
    氳
    0.53
    事が
    0.49
    㻁
    0.48
    闓
    0.47
    を作り
    0.47
     बसपा
    0.45
    暠
    0.45
    Configs
    0.44
     कामयाब
    0.44
    POSITIVE LOGITS
    en
    0.57
    t
    0.49
    r
    0.46
    s
    0.46
    p
    0.44
     to
    0.44
    m
    0.43
    j
    0.41
    l
    0.41
    '
    0.40
    Act Density 0.001%

    No Known Activations