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

    Neuronpedia

    INDEX
    Explanations

    restaurant descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mano
    -0.07
     Nan
    -0.06
     cabeza
    -0.06
    unakan
    -0.06
    的话
    -0.06
    (trim
    -0.06
     cancel
    -0.06
     folded
    -0.06
    альную
    -0.06
    iali
    -0.06
    POSITIVE LOGITS
     ///↵
    0.07
     městě
    0.06
    рать
    0.06
    .ContainsKey
    0.06
     shrine
    0.06
     В
    0.06
    Advisor
    0.06
     �
    0.06
    “It
    0.06
     alloc
    0.06
    Act Density 0.049%

    No Known Activations