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

    Neuronpedia

    INDEX
    Explanations

    sooner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pand
    -0.07
     Narrow
    -0.06
     importantes
    -0.06
    Sus
    -0.06
    /colors
    -0.06
    тами
    -0.06
     Ná
    -0.06
     gauss
    -0.06
     mensagem
    -0.06
    ѓ
    -0.06
    POSITIVE LOGITS
    Website
    0.07
     defer
    0.06
    един
    0.06
     oma
    0.06
    inating
    0.06
     deren
    0.06
    LETTE
    0.06
     acuerdo
    0.06
    .SizeType
    0.06
     Moment
    0.06
    Act Density 0.003%

    No Known Activations