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

    Neuronpedia

    INDEX
    Explanations

    option 1 or share mode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monterey
    0.40
     lifeless
    0.39
     குழ
    0.38
     فلس
    0.38
    క్షి
    0.38
     cheese
    0.38
    nten
    0.37
     Antioxid
    0.36
    ್ಯೂ
    0.36
     abandonar
    0.36
    POSITIVE LOGITS
    chall
    0.43
    ético
    0.41
    Déc
    0.40
     सुविधा
    0.39
     dissociated
    0.38
    Deck
    0.38
    greeting
    0.38
    CREATED
    0.38
    不但
    0.37
    不僅
    0.37
    Act Density 0.001%

    No Known Activations