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

    Neuronpedia

    INDEX
    Explanations

    questions/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responsables
    -0.10
     responsible
    -0.08
    uve
    -0.08
     delectable
    -0.08
    etal
    -0.08
     responsable
    -0.08
     entsprechende
    -0.08
     arduous
    -0.07
     painstaking
    -0.07
     responsáveis
    -0.07
    POSITIVE LOGITS
     wondering
    0.12
     是否
    0.10
     feasibility
    0.10
     Question
    0.10
    Question
    0.09
    .Question
    0.09
    是否
    0.09
     sonho
    0.09
     apakah
    0.09
    Fe
    0.09
    Act Density 0.146%

    No Known Activations