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

    Neuronpedia

    INDEX
    Explanations

    verb definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     favorites
    -0.06
    (write
    -0.06
    esi
    -0.06
    >Hello
    -0.06
     Leigh
    -0.06
    idos
    -0.06
    (language
    -0.06
    NUM
    -0.06
     Joyce
    -0.06
    /Header
    -0.06
    POSITIVE LOGITS
     conc
    0.07
    _performance
    0.07
     clases
    0.07
     Screens
    0.07
     Leads
    0.06
    ันก
    0.06
    essential
    0.06
    .column
    0.06
     сель
    0.06
     Stud
    0.06
    Act Density 0.020%

    No Known Activations