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

    Neuronpedia

    INDEX
    Explanations

    mezzanine debt or tranches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    1.13
    í
    1.08
    ால்
    1.06
    ఆర్
    1.05
    ý
    1.05
    e
    1.03
    خدام
    0.99
     you
    0.97
    eurs
    0.97
    偖
    0.95
    POSITIVE LOGITS
    ק
    1.46
    ش
    1.06
     дороги
    1.05
    ation
    0.98
    g
    0.97
    t
    0.96
     flange
    0.94
     раствор
    0.94
    य
    0.89
    4
    0.89
    Act Density 0.000%

    No Known Activations