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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interrog
    -0.07
     Türkiye
    -0.07
     iterator
    -0.06
     feast
    -0.06
     Called
    -0.06
    One
    -0.06
    _exempt
    -0.06
     corpses
    -0.06
    Example
    -0.06
     mansion
    -0.06
    POSITIVE LOGITS
    (icon
    0.06
    ")->
    0.06
     عقد
    0.06
    šla
    0.06
    ایسه
    0.06
     Sox
    0.06
     godt
    0.06
     obl
    0.06
    xCE
    0.06
    .mdl
    0.06
    Act Density 0.045%

    No Known Activations