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

    Neuronpedia

    INDEX
    Explanations

    why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    дут
    -0.07
     Některá
    -0.07
     Sand
    -0.06
     sentiments
    -0.06
     �
    -0.06
     His
    -0.06
     defends
    -0.06
    sense
    -0.06
     Quentin
    -0.06
    Sense
    -0.06
    POSITIVE LOGITS
     vicinity
    0.06
    르고
    0.06
     automat
    0.06
    VAL
    0.06
    located
    0.06
     řek
    0.06
    jm
    0.06
    oled
    0.06
    �
    0.06
    В
    0.06
    Act Density 0.006%

    No Known Activations