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

    Neuronpedia

    INDEX
    Explanations

    Table references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Regression
    -0.07
     passionate
    -0.07
    oric
    -0.06
    tool
    -0.06
    (properties
    -0.06
     snack
    -0.06
    $image
    -0.06
     gasoline
    -0.06
    	stats
    -0.06
     Grande
    -0.06
    POSITIVE LOGITS
     archit
    0.06
    Chair
    0.06
    ABCDEFGHI
    0.06
    localStorage
    0.06
     incorporates
    0.06
    еру
    0.06
    84
    0.06
    alom
    0.06
    sez
    0.06
    �
    0.06
    Act Density 0.019%

    No Known Activations