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

    Neuronpedia

    INDEX
    Explanations

    there/here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hindi
    -0.08
    алі
    -0.08
     lee
    -0.07
     Till
    -0.07
     virtuelle
    -0.07
     Höhen
    -0.07
     virtu
    -0.07
    č
    -0.07
    леген
    -0.07
    бай
    -0.07
    POSITIVE LOGITS
     હાજ
    0.08
     பழ
    0.08
     flush
    0.08
     இருப்ப
    0.08
     imperfect
    0.08
    flush
    0.08
    Jets
    0.07
    ’installation
    0.07
     են
    0.07
     उपस्थित
    0.07
    Act Density 0.002%

    No Known Activations