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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ومد
    -0.08
     Hispanic
    -0.08
     माय
    -0.08
     elevations
    -0.08
     contempla
    -0.08
    Detection
    -0.08
     deport
    -0.08
     कृष्ण
    -0.08
     осталось
    -0.08
    Inicial
    -0.08
    POSITIVE LOGITS
     The
    0.09
     Funktionen
    0.08
     paradigma
    0.08
     Swap
    0.08
    .swap
    0.08
     Seit
    0.08
     Functions
    0.08
     Iter
    0.08
     functions
    0.08
     sağ
    0.07
    Act Density 0.002%

    No Known Activations