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

    Neuronpedia

    INDEX
    Explanations

    essays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Svc
    -0.07
    Extern
    -0.07
    Page
    -0.06
     blending
    -0.06
    proved
    -0.06
    AAP
    -0.06
     Translator
    -0.06
    _Window
    -0.06
     kèm
    -0.06
    stre
    -0.06
    POSITIVE LOGITS
    [current
    0.06
     acqu
    0.06
    ัตน
    0.06
    0.06
    0.06
    Dé
    0.06
     trif
    0.06
     pragmatic
    0.05
     hiçbir
    0.05
     deployments
    0.05
    Act Density 0.053%

    No Known Activations