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

    Neuronpedia

    INDEX
    Explanations

    rising tide or shifting landscape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     each
    0.76
     incre
    0.74
    마다
    0.72
     mendorong
    0.68
     existence
    0.67
     Each
    0.66
    縝
    0.66
     reassuring
    0.66
    each
    0.64
     sürekli
    0.63
    POSITIVE LOGITS
     waters
    0.87
     scene
    0.86
     ball
    0.83
     stage
    0.79
     picture
    0.78
     groundwork
    0.78
     sails
    0.78
    imeric
    0.77
     Bühne
    0.76
     spotlight
    0.75
    Act Density 0.342%

    No Known Activations