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

    Neuronpedia

    INDEX
    Explanations

    factor pairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Installation
    -0.08
     Noël
    -0.08
     Collective
    -0.08
     sampled
    -0.07
     Quem
    -0.07
     Franken
    -0.07
     Curt
    -0.07
     Quad
    -0.07
     DU
    -0.07
     Distributed
    -0.07
    POSITIVE LOGITS
     страна
    0.08
     fiz
    0.08
    .lookup
    0.08
    物流
    0.08
    _lookup
    0.08
    .display
    0.08
     گذاری
    0.08
     lesson
    0.08
    .look
    0.08
    Looking
    0.07
    Act Density 0.009%

    No Known Activations