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

    Neuronpedia

    INDEX
    Explanations

    left or right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orientation
    -0.07
    舌
    -0.07
     Norte
    -0.07
    isease
    -0.06
     Pipes
    -0.06
    ments
    -0.06
     quella
    -0.06
    �
    -0.06
     PLA
    -0.06
    金
    -0.06
    POSITIVE LOGITS
    ."',
    0.06
     vượt
    0.06
     vás
    0.06
     daring
    0.06
    )',
    0.06
     convoy
    0.06
     Voting
    0.06
    South
    0.06
    ?'
    0.06
    Jessica
    0.06
    Act Density 0.014%

    No Known Activations