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

    Neuronpedia

    INDEX
    Explanations

    absorption, acceptance, permanently, followed by, dead-end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estructive
    1.62
    ত
    1.60
    ного
    1.55
    य
    1.55
    स
    1.54
    y
    1.54
     jsonify
    1.50
    𝘢
    1.46
    ist
    1.43
    ક
    1.42
    POSITIVE LOGITS
    o
    1.99
    ে
    1.80
     miliar
    1.76
    ه
    1.57
     सटे
    1.51
     disse
    1.49
     drenched
    1.49
     acquainted
    1.47
    תר
    1.45
    ेर
    1.41
    Act Density 0.087%

    No Known Activations