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

    Neuronpedia

    INDEX
    Explanations

    dice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Winners
    -0.07
     Depths
    -0.07
    _probs
    -0.07
     транс
    -0.07
    (letter
    -0.06
     subjected
    -0.06
    <len
    -0.06
     Gwen
    -0.06
     pruning
    -0.06
     nrows
    -0.06
    POSITIVE LOGITS
     dice
    0.17
     Dice
    0.16
    Dice
    0.15
     diced
    0.11
    dice
    0.10
    _dice
    0.09
     Miscellaneous
    0.07
    iene
    0.07
    cej
    0.07
    dız
    0.06
    Act Density 0.002%

    No Known Activations