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

    Neuronpedia

    INDEX
    Explanations

    Flow state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cub
    -0.08
    تماد
    -0.08
     Airbus
    -0.07
     eager
    -0.07
    िष्ट
    -0.07
    gação
    -0.07
     Mandarin
    -0.07
    ப்படுகிறது
    -0.07
    麼
    -0.07
     Conclusions
    -0.07
    POSITIVE LOGITS
     obsc
    0.07
    restrict
    0.07
    hemeral
    0.07
    ാത്ര
    0.07
     improb
    0.07
     diffusion
    0.07
     criterion
    0.07
    遭
    0.07
     censorship
    0.07
    ેઠ
    0.07
    Act Density 0.001%

    No Known Activations