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

    Neuronpedia

    INDEX
    Explanations

    not a true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esperamos
    0.62
     consideramos
    0.49
     বিচারপতি
    0.47
     uus
    0.46
     വ്യക്ത
    0.45
     Bedroom
    0.43
    ევრი
    0.43
     índices
    0.43
    বিত্র
    0.43
     მაშინ
    0.43
    POSITIVE LOGITS
     but
    0.52
    但不
    0.45
    (+)
    0.44
     heron
    0.43
     allo
    0.43
    大陆
    0.42
    .'
    0.42
     bary
    0.42
     Heron
    0.42
    .'</
    0.42
    Act Density 0.004%

    No Known Activations