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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irradi
    -0.08
    _ESCAPE
    -0.07
    Vel
    -0.07
    pla
    -0.07
    (Transform
    -0.06
    +self
    -0.06
    	scroll
    -0.06
    _IMPORTED
    -0.06
     происходит
    -0.06
     #@
    -0.06
    POSITIVE LOGITS
    [:
    0.06
    找
    0.06
    ])↵↵↵
    0.06
    .createElement
    0.06
     >
    0.06
    ;;
    0.06
     können
    0.06
     propose
    0.06
     Among
    0.06
     ↵ ↵
    0.05
    Act Density 0.007%

    No Known Activations