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

    Neuronpedia

    INDEX
    Explanations

    UI/UX design

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,__
    -0.08
     Alive
    -0.07
    Alive
    -0.07
    +↵
    -0.06
    walk
    -0.06
     estable
    -0.06
     XPath
    -0.06
     Claus
    -0.06
    در
    -0.06
    Mir
    -0.06
    POSITIVE LOGITS
    /help
    0.06
    VF
    0.06
     sıcak
    0.06
    */
↵
    0.06
     проф
    0.06
     강남
    0.06
    atching
    0.06
    _LIGHT
    0.06
     overridden
    0.05
    .quality
    0.05
    Act Density 0.032%

    No Known Activations