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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     association
    -0.08
     여러분
    -0.08
     dinheiro
    -0.08
     Formação
    -0.08
     азарт
    -0.08
     Rádio
    -0.08
     associação
    -0.08
     Raiders
    -0.08
     түрлі
    -0.07
     Association
    -0.07
    POSITIVE LOGITS
     Мак
    0.08
    ingu
    0.08
     doivent
    0.07
    isciplinary
    0.07
    ?s
    0.07
    etsy
    0.07
     Mc
    0.07
    ு�
    0.07
     LP
    0.07
    ्ले
    0.07
    Act Density 0.003%

    No Known Activations