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

    Neuronpedia

    INDEX
    Explanations

    pose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uses
    -0.96
    vs
    -0.79
     uses
    -0.68
    pose
    -0.68
     operator
    -0.65
     use
    -0.57
    pha
    -0.54
    Vs
    -0.54
    Uses
    -0.50
    VS
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.95
    interopRequire
    0.88
    IndentedString
    0.86
    transQ
    0.85
    
    0.81
    horabuena
    0.81
     utafitiHapana
    0.81
     propOrder
    0.80
     nahilalakip
    0.80
     فريبيس
    0.79
    Act Density 0.483%

    No Known Activations