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

    Neuronpedia

    INDEX
    Explanations

    Amazon S3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мини
    -0.09
     encargado
    -0.09
     Jr
    -0.08
     televisión
    -0.08
     रव
    -0.08
     bevatten
    -0.08
     raíz
    -0.08
    ريق
    -0.08
     raíces
    -0.08
    cadena
    -0.08
    POSITIVE LOGITS
     Experiences
    0.08
    ยอด
    0.08
     quota
    0.07
     modalidade
    0.07
     benchmark
    0.07
     Performance
    0.07
     Double
    0.07
     Italiano
    0.07
     Provision
    0.07
     Economy
    0.07
    Act Density 0.005%

    No Known Activations