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

    Neuronpedia

    INDEX
    Explanations

    containers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atif
    -0.07
     kelim
    -0.07
    atory
    -0.07
     veterin
    -0.06
     виконав
    -0.06
    atürk
    -0.06
    ền
    -0.06
    iod
    -0.06
    upe
    -0.06
     cows
    -0.06
    POSITIVE LOGITS
     delight
    0.07
     secrets
    0.06
    -speed
    0.06
    icious
    0.06
    Sprite
    0.06
    ざ
    0.06
    .Current
    0.06
     spoon
    0.06
     overlooked
    0.06
     assure
    0.06
    Act Density 0.007%

    No Known Activations