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

    Neuronpedia

    INDEX
    Explanations

    particularly important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     []);
    1.07
     '');
    1.07
    okhlov
    1.04
     Neues
    1.02
     yapı
    0.99
    个小时
    0.98
     libres
    0.97
    就连
    0.96
     sabía
    0.96
     podríamos
    0.94
    POSITIVE LOGITS
    INATION
    1.09
    WAY
    1.09
    ↵
    1.08
    क
    1.05
    ก
    1.05
    ÃO
    1.04
    го
    1.03
        
    1.01
    ATION
    1.01
    ך
    1.00
    Act Density 0.806%

    No Known Activations