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

    Neuronpedia

    INDEX
    Explanations

    removing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Detect
    -0.07
     absorb
    -0.07
     stomach
    -0.06
     jog
    -0.06
     
↵
    -0.06
    xmax
    -0.06
    ».
    -0.06
     NW
    -0.06
    .Rows
    -0.06
     Powder
    -0.06
    POSITIVE LOGITS
    -brand
    0.07
    Å
    0.06
    ляет
    0.06
    	AL
    0.06
     khảo
    0.06
     MainMenu
    0.06
    атем
    0.06
    gency
    0.06
    	fn
    0.06
    ていない
    0.06
    Act Density 0.116%

    No Known Activations