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

    Neuronpedia

    INDEX
    Explanations

    cursor pointer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     )
    0.46
     Approach
    0.41
     ट्रोल
    0.40
     );
    0.40
     motocicleta
    0.38
     motorist
    0.38
     vulcan
    0.36
     ]
    0.36
     नाग
    0.36
     esbo
    0.36
    POSITIVE LOGITS
    ätten
    0.41
    共享
    0.39
    ätzen
    0.38
     ജീവിത
    0.38
    inée
    0.38
     استعداد
    0.38
     halting
    0.37
    subject
    0.37
     pocket
    0.37
     கொள்
    0.37
    Act Density 0.000%

    No Known Activations