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

    Neuronpedia

    INDEX
    Explanations

    source of authority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.24
     a
    1.23
     వచ్చిన
    1.02
     最
    0.99
     將
    0.98
     រ
    0.97
     书
    0.96
    ták
    0.95
    }=\
    0.95
    }=
    0.94
    POSITIVE LOGITS
    0
    1.48
    the
    1.34
    ad
    1.13
    ի
    1.13
     authority
    1.10
    <0x80>
    1.09
    on
    1.04
    :
    1.04
    ב
    1.00
    ۰
    0.98
    Act Density 0.086%

    No Known Activations