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

    Neuronpedia

    INDEX
    Explanations

    variant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Introduction
    -0.07
     europe
    -0.07
     decreases
    -0.07
    448
    -0.07
    _ll
    -0.07
    Introduction
    -0.07
    Castle
    -0.07
    eneration
    -0.06
     MouseButton
    -0.06
    stored
    -0.06
    POSITIVE LOGITS
     variant
    0.09
     nh
    0.08
    ват
    0.07
    ant
    0.07
    endent
    0.07
    Variant
    0.07
    ai
    0.07
    ate
    0.07
    AN
    0.07
     disrupt
    0.06
    Act Density 0.007%

    No Known Activations