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

    Neuronpedia

    INDEX
    Explanations

    technical components and expansions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    র
    0.56
     garantizar
    0.49
     что
    0.46
     nuestro
    0.45
     sebesar
    0.44
     гаран
    0.43
    আমার
    0.43
    र
    0.43
     viewDidLoad
    0.43
     crit
    0.43
    POSITIVE LOGITS
    HS
    0.50
    ile
    0.46
    onta
    0.44
    lista
    0.43
    cakes
    0.43
     fringes
    0.43
     Fonte
    0.43
    ristown
    0.42
    amped
    0.42
    ga
    0.42
    Act Density 0.000%

    No Known Activations