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

    Neuronpedia

    INDEX
    Explanations

    guard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cricket
    -0.06
     cré
    -0.06
    oš
    -0.06
     moy
    -0.06
    ulet
    -0.06
    expect
    -0.06
     crus
    -0.06
    nThe
    -0.06
     entrev
    -0.06
    انيا
    -0.06
    POSITIVE LOGITS
     podle
    0.07
    GraphNode
    0.06
    (Have
    0.06
     blog
    0.06
    /XMLSchema
    0.06
    _json
    0.06
    mlin
    0.06
     Prague
    0.06
    _blog
    0.06
     Consumer
    0.06
    Act Density 0.001%

    No Known Activations