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

    Neuronpedia

    INDEX
    Explanations

    depiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.01
     Anſ
    -0.96
     fubject
    -0.96
     poffible
    -0.96
     themſelves
    -0.95
     preſent
    -0.94
     itſelf
    -0.94
     deſt
    -0.93
     المعيارى
    -0.93
    Personensuche
    -0.93
    POSITIVE LOGITS
    ing
    0.59
    ru
    0.55
    nelle
    0.54
    r
    0.54
    na
    0.53
    ser
    0.53
    re
    0.52
    so
    0.52
    du
    0.52
    no
    0.51
    Act Density 1.714%

    No Known Activations