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

    Neuronpedia

    INDEX
    Explanations

    sugar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stored
    -0.07
    には
    -0.06
     Calculation
    -0.06
     هذه
    -0.06
    ,F
    -0.06
    other
    -0.06
    *N
    -0.06
    _NEW
    -0.06
    pton
    -0.06
    -rays
    -0.06
    POSITIVE LOGITS
     conclusive
    0.07
     기준
    0.07
    946
    0.07
     composing
    0.06
     justices
    0.06
     keyed
    0.06
     ऋ
    0.06
     humorous
    0.06
    -operator
    0.06
    243
    0.06
    Act Density 0.003%

    No Known Activations