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

    Neuronpedia

    INDEX
    Explanations

    I'm / I do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserController
    0.53
     proguard
    0.49
    Downloading
    0.48
    startGame
    0.47
     предупре
    0.47
    ήμε
    0.46
     diarrhoea
    0.46
    បើ
    0.46
    inputFile
    0.45
    inputValue
    0.45
    POSITIVE LOGITS
    ing
    0.55
     sort
    0.50
     besi
    0.49
     P
    0.45
    ari
    0.45
    ingar
    0.45
     Inn
    0.44
    ceso
    0.44
     R
    0.43
    arat
    0.42
    Act Density 0.003%

    No Known Activations