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

    Neuronpedia

    INDEX
    Explanations

    say number

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dylan
    0.79
     општи
    0.77
     viking
    0.76
     Gillette
    0.75
    ędzie
    0.74
     Stevie
    0.73
     عكس
    0.72
     Lillian
    0.72
     Fleetwood
    0.71
     XPS
    0.71
    POSITIVE LOGITS
    าย
    0.63
     mensagens
    0.60
     rilev
    0.59
    យ
    0.58
     mesurer
    0.58
     adhé
    0.57
    sema
    0.57
     nachdem
    0.56
    作成
    0.56
     πυ
    0.56
    Act Density 0.016%

    No Known Activations