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

    Neuronpedia

    INDEX
    Explanations

    tree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     governing
    -0.09
    assion
    -0.08
     training
    -0.08
    celer
    -0.07
    cription
    -0.07
     deriving
    -0.07
     acel
    -0.07
     moral
    -0.07
    Regression
    -0.07
    -sub
    -0.07
    POSITIVE LOGITS
     إزالة
    0.09
     problèmes
    0.09
     większo
    0.09
     Serviços
    0.08
     ઘણા
    0.08
     Sunn
    0.08
     기사
    0.08
     rugs
    0.08
     Dienstleistungen
    0.08
     llaw
    0.08
    Act Density 0.008%

    No Known Activations