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

    Neuronpedia

    INDEX
    Explanations

    snacks and candies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     springs
    -0.07
    (IR
    -0.07
    NFL
    -0.06
    pun
    -0.06
    in
    -0.06
     tabs
    -0.06
    圧
    -0.06
     //!
    -0.06
    _damage
    -0.06
    =read
    -0.06
    POSITIVE LOGITS
    ientos
    0.08
     incurred
    0.07
    &view
    0.06
     Nicola
    0.06
    +%
    0.06
     shameful
    0.06
     tyto
    0.06
     purported
    0.06
     biểu
    0.06
    _DISABLE
    0.06
    Act Density 0.041%

    No Known Activations