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

    Neuronpedia

    INDEX
    Explanations

    technology, model, import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    溟
    0.40
     critica
    0.37
     elettronica
    0.37
     जैसे
    0.37
     rectas
    0.37
    والفق
    0.37
    വൃ
    0.36
     cruisers
    0.36
     தி
    0.35
     spatial
    0.35
    POSITIVE LOGITS
    Number
    0.41
    Rib
    0.36
     MasterCard
    0.36
     ધર
    0.36
     env
    0.36
     suspicious
    0.36
     চম
    0.35
    🏼
    0.35
    icat
    0.35
    aniem
    0.34
    Act Density 0.000%

    No Known Activations