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

    Neuronpedia

    INDEX
    Explanations

    Code/Math/File paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stuffing
    -0.08
    ,$
    -0.08
     fills
    -0.08
    PAY
    -0.08
    ++];↵
    -0.08
     सहाय
    -0.08
    _RED
    -0.08
     staffed
    -0.07
     abuse
    -0.07
     assistance
    -0.07
    POSITIVE LOGITS
     ومت
    0.09
    ери
    0.09
     consistently
    0.09
     variability
    0.09
    ерите
    0.08
    intel
    0.08
     kompat
    0.08
     vseh
    0.08
    inene
    0.08
    ങ്ങളിലും
    0.08
    Act Density 0.034%

    No Known Activations