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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izen
    -0.08
    Sum
    -0.07
    ieu
    -0.07
     hazard
    -0.07
    노
    -0.07
    /(
    -0.07
    erva
    -0.07
    endon
    -0.07
    istribution
    -0.07
     Nu
    -0.07
    POSITIVE LOGITS
     academics
    0.07
    喟
    0.07
    _LAYOUT
    0.07
    没有必要
    0.07
     dés
    0.07
     PROVIDED
    0.07
    _INCLUDED
    0.07
     JSONException
    0.07
     traumat
    0.07
     אחרות
    0.06
    Act Density 0.019%

    No Known Activations