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

    Neuronpedia

    INDEX
    Explanations

    humor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mariners
    -0.09
     envi
    -0.09
     mitt
    -0.09
     مجاني
    -0.09
     specimens
    -0.08
     Wilmington
    -0.08
    Mitt
    -0.08
     sinal
    -0.08
     LAN
    -0.08
     muestras
    -0.08
    POSITIVE LOGITS
     absurd
    0.09
     surreal
    0.08
     leh
    0.08
     revolves
    0.08
     interplay
    0.08
    剧情
    0.08
     explore
    0.08
     сюжет
    0.08
     revolve
    0.08
    角色
    0.08
    Act Density 0.024%

    No Known Activations