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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хто
    -0.07
    _with
    -0.06
    floating
    -0.06
     spécial
    -0.06
     nbytes
    -0.06
    卫
    -0.06
     Observation
    -0.06
     precisely
    -0.06
    Deal
    -0.06
     투
    -0.06
    POSITIVE LOGITS
     Increasing
    0.07
    ασία
    0.07
    creasing
    0.06
    ελ
    0.06
    (){
    0.06
    ersistent
    0.06
     LAB
    0.06
     skins
    0.06
     hides
    0.06
    ूप
    0.06
    Act Density 0.009%

    No Known Activations