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

    Neuronpedia

    INDEX
    Explanations

    schema

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.07
     themſelves
    -1.02
     itſelf
    -1.00
     iſt
    -0.96
    Meeting
    -0.96
    meeting
    -0.95
     ſind
    -0.95
     meeting
    -0.94
     himſelf
    -0.94
     MEETING
    -0.91
    POSITIVE LOGITS
    ly
    0.68
     of
    0.57
    tu
    0.56
    i
    0.54
    land
    0.54
    t
    0.54
    ary
    0.53
    h
    0.52
    dom
    0.50
    le
    0.49
    Act Density 1.259%

    No Known Activations