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

    Neuronpedia

    INDEX
    Explanations

    letter shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuisance
    -0.08
    .override
    -0.08
     recommendations
    -0.07
    فا
    -0.07
     scenarios
    -0.07
    .prompt
    -0.07
    .Broadcast
    -0.07
     impacts
    -0.07
     facilities
    -0.07
     oracle
    -0.07
    POSITIVE LOGITS
     sideways
    0.10
     Pisa
    0.09
     lef
    0.09
    翼
    0.09
     angled
    0.09
     waving
    0.09
     hollow
    0.09
     esquerda
    0.09
     सफ
    0.09
    描
    0.09
    Act Density 0.011%

    No Known Activations