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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simultaneously
    -0.07
    .print
    -0.07
    SYNC
    -0.07
     مما
    -0.07
    /testing
    -0.07
    .dis
    -0.07
    随着
    -0.06
    abilia
    -0.06
     tod
    -0.06
    Ὸ
    -0.06
    POSITIVE LOGITS
    �
    0.07
     machen
    0.07
    (ir
    0.07
    أغلب
    0.06
     Mormons
    0.06
     temperatures
    0.06
    冰淇淋
    0.06
    "]/
    0.06
     GIF
    0.06
     rational
    0.06
    Act Density 0.004%

    No Known Activations