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

    Neuronpedia

    INDEX
    Explanations

    Code Headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canvas
    -0.07
     Butterfly
    -0.07
     travel
    -0.07
     fruit
    -0.07
    us
    -0.07
     côté
    -0.07
     galleries
    -0.07
     spring
    -0.07
     Swamp
    -0.06
     Fre
    -0.06
    POSITIVE LOGITS
    >')
    0.07
    규
    0.07
    Add
    0.06
     _$
    0.06
     "></
    0.06
     xamarin
    0.06
     �
    0.06
    이라는
    0.06
     ศ
    0.06
    %");↵
    0.06
    Act Density 0.004%

    No Known Activations