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

    Neuronpedia

    INDEX
    Explanations

    say "jury"

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    \Factory
    -0.07
     najbli
    -0.07
    SEND
    -0.07
    给
    -0.07
    �
    -0.07
     Cobb
    -0.06
     ----
    -0.06
    Put
    -0.06
     diplom
    -0.06
    拿
    -0.06
    POSITIVE LOGITS
    ENCIL
    0.07
     efect
    0.07
    Ϋ
    0.07
    .SelectedValue
    0.07
     Tüm
    0.06
    헿
    0.06
     Amir
    0.06
    GenerationStrategy
    0.06
    䃅
    0.06
    Insurance
    0.06
    Act Density 0.009%

    No Known Activations