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

    Neuronpedia

    INDEX
    Explanations

    attention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foods
    -0.08
     भव
    -0.08
     framt
    -0.08
     miscellaneous
    -0.08
     काय
    -0.08
     conventions
    -0.08
    zeros
    -0.07
     আহ
    -0.07
     futurs
    -0.07
     umum
    -0.07
    POSITIVE LOGITS
     individualized
    0.13
     Betreuung
    0.11
     внимание
    0.11
     atención
    0.11
     personalized
    0.11
     attentive
    0.10
    Attention
    0.10
     atenção
    0.10
     atendimento
    0.10
     Personalized
    0.10
    Act Density 0.029%

    No Known Activations