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

    Neuronpedia

    INDEX
    Explanations

    first name followed by last name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ূনতম
    0.46
    segaretro
    0.45
    ResumeLayout
    0.42
    ร้อม
    0.41
    凛
    0.40
    nydd
    0.39
    kubectl
    0.39
    sdx
    0.39
    互联网
    0.38
    geoning
    0.38
    POSITIVE LOGITS
     Harmon
    0.43
     MILLER
    0.43
    λα
    0.41
     farm
    0.41
     Burk
    0.40
     stocks
    0.39
    ulah
    0.39
     plug
    0.38
     orchard
    0.38
     stru
    0.38
    Act Density 0.002%

    No Known Activations