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

    Neuronpedia

    INDEX
    Explanations

    unable to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ড
    1.21
     in
    1.05
     is
    1.05
    };
    0.98
    کار
    0.98
    তা
    0.92
     hostels
    0.91
    ט
    0.91
     extérieur
    0.91
    Ι
    0.91
    POSITIVE LOGITS
    an
    1.35
    .
    1.30
    ong
    1.08
    ac
    1.01
     फॉर
    1.00
    ла
    0.99
    ك
    0.98
    -
    0.97
    bed
    0.96
    AIN
    0.95
    Act Density 0.002%

    No Known Activations