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

    Neuronpedia

    INDEX
    Explanations

    wald

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iotic
    -0.07
    ificacion
    -0.07
     Fuck
    -0.07
     engaging
    -0.07
    ocop
    -0.06
    ondon
    -0.06
     Fan
    -0.06
    ивання
    -0.06
    esion
    -0.06
    })(
    -0.06
    POSITIVE LOGITS
     Wald
    0.08
     Vlad
    0.07
    临
    0.07
     Cele
    0.07
    臨
    0.07
     Claud
    0.07
     Quartz
    0.07
    ald
    0.07
    тов
    0.07
     Alberto
    0.06
    Act Density 0.016%

    No Known Activations