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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーパー
    -0.07
     BEN
    -0.07
     tàu
    -0.07
     theaters
    -0.07
    віль
    -0.07
     China
    -0.07
    })(
    -0.07
     semana
    -0.06
     hom
    -0.06
     Albany
    -0.06
    POSITIVE LOGITS
    余
    0.07
     pornos
    0.07
     sacked
    0.06
     intrigued
    0.06
    itorio
    0.06
    作用
    0.06
     А
    0.06
    /person
    0.06
    ificial
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations