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

    Neuronpedia

    INDEX
    Explanations

    structures and components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.91
     esternos
    -0.66
    Controllo
    -0.63
     متعلقه
    -0.60
     الرياضيه
    -0.59
     saites
    -0.59
    ínsula
    -0.58
    >();
    -0.58
    lamabad
    -0.58
    GraphicsUnit
    -0.57
    POSITIVE LOGITS
     felizes
    0.56
     sicura
    0.56
     craters
    0.54
     terrarium
    0.54
     cockroach
    0.53
     sunburn
    0.53
     glassware
    0.52
     winery
    0.52
     apricots
    0.52
     exciter
    0.52
    Act Density 0.044%

    No Known Activations