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

    Neuronpedia

    INDEX
    Explanations

    say "av" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    문의
    -0.06
    Assets
    -0.06
     /[
    -0.06
    .Ş
    -0.06
     seguridad
    -0.06
    onn
    -0.06
    etta
    -0.06
    ють
    -0.05
     yyyy
    -0.05
    tery
    -0.05
    POSITIVE LOGITS
     ende
    0.07
     cose
    0.07
     NK
    0.07
     hob
    0.07
     comprehension
    0.06
     subdiv
    0.06
     Ches
    0.06
    InvalidOperationException
    0.06
     ade
    0.06
     AWS
    0.06
    Act Density 0.002%

    No Known Activations