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

    Neuronpedia

    INDEX
    Explanations

    schedule or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.60
     in
    0.52
     the
    0.51
     (
    0.50
     to
    0.49
      
    0.47
     a
    0.46
     one
    0.46
     end
    0.44
     can
    0.44
    POSITIVE LOGITS
    玖章
    0.44
    GEBURTS
    0.43
    𒅴
    0.42
     bottlene
    0.42
     للمعارف
    0.41
     गिवन
    0.41
    getBlueTeam
    0.41
    ╽
    0.41
     CustB
    0.40
    urètre
    0.40
    Act Density 0.000%

    No Known Activations