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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Morse
    -0.06
    γκο
    -0.06
     Negative
    -0.06
    <Person
    -0.06
     producción
    -0.06
    _doc
    -0.06
    ounty
    -0.06
     PVC
    -0.06
    殺
    -0.06
     Lookup
    -0.06
    POSITIVE LOGITS
    '},
↵
    0.07
    lying
    0.07
    reating
    0.07
    /result
    0.07
    .SelectedItem
    0.06
    (model
    0.06
    xfd
    0.06
    Json
    0.06
    ared
    0.06
    _rename
    0.06
    Act Density 0.046%

    No Known Activations