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

    Neuronpedia

    INDEX
    Explanations

    php code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    2.51
    en
    2.27
    ল
    1.92
    ження
    1.88
     kert
    1.85
    न
    1.80
     agar
    1.79
    ations
    1.79
     ponds
    1.76
    Saat
    1.76
    POSITIVE LOGITS
     admirably
    1.71
     przyczyn
    1.67
    াজ
    1.61
    lysis
    1.56
    ἥ
    1.50
     direta
    1.47
     cinética
    1.47
    1.45
     ard
    1.45
     суще
    1.45
    Act Density 0.000%

    No Known Activations