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

    Neuronpedia

    INDEX
    Explanations

    sole aim or basis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    1.23
    r
    1.18
    시
    1.18
    }$.
    1.09
    اي
    1.09
    体
    1.07
    NI
    1.04
    は
    1.04
     was
    1.03
    N
    1.02
    POSITIVE LOGITS
     are
    1.20
    ’
    1.03
    ivät
    1.02
    itt
    1.02
    ra
    1.01
     Sole
    0.98
    <0x80>
    0.97
    are
    0.94
    ões
    0.89
    men
    0.89
    Act Density 0.008%

    No Known Activations