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

    Neuronpedia

    INDEX
    Explanations

    lists, generating, new, letter, directories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Secondo
    0.54
    睄
    0.52
    Brun
    0.51
    Strateg
    0.50
    Necess
    0.50
    letos
    0.49
    Clientes
    0.49
    Consent
    0.49
    ificação
    0.48
     estratégia
    0.48
    POSITIVE LOGITS
    t
    0.77
    l
    0.67
    c
    0.59
    z
    0.55
     breeders
    0.53
    an
    0.52
    p
    0.51
    al
    0.50
    y
    0.50
    f
    0.50
    Act Density 0.001%

    No Known Activations