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

    Neuronpedia

    INDEX
    Explanations

    json structure for code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ன்ஹீ
    0.41
     }]);
    0.39
     neuro
    0.38
     debut
    0.38
     সাজেশন
    0.37
     рекомендации
    0.37
    انوي
    0.37
    occhi
    0.37
     დიდი
    0.37
    เบียน
    0.36
    POSITIVE LOGITS
     "@
    0.47
    ]`
    0.41
    resolve
    0.41
    Transformer
    0.41
     benc
    0.40
     mst
    0.39
     `
    0.39
    "@
    0.39
    rative
    0.39
    TYPE
    0.38
    Act Density 0.000%

    No Known Activations