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

    Neuronpedia

    INDEX
    Explanations

    links and scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complète
    0.75
    бло
    0.72
     agré
    0.70
     œufs
    0.69
    ചന
    0.69
     donnent
    0.69
     commen
    0.69
     بندی
    0.68
     ajoute
    0.67
     événements
    0.67
    POSITIVE LOGITS
    дентификаторы
    0.96
    ens
    0.77
    s
    0.76
     Confeder
    0.73
    $&
    0.71
    if
    0.70
    catch
    0.70
     Primeira
    0.70
    一看
    0.70
    PROTO
    0.69
    Act Density 0.000%

    No Known Activations