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

    Neuronpedia

    INDEX
    Explanations

    learn more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ainte
    0.34
     Constit
    0.34
    ംഗ്
    0.34
    ક્રિયા
    0.32
    მი
    0.31
    HV
    0.30
    imine
    0.30
     vzduchu
    0.30
    靼
    0.30
    ாஹ
    0.30
    POSITIVE LOGITS
     about
    0.96
     more
    0.82
    更多
    0.77
     về
    0.73
     tentang
    0.73
     عن
    0.72
    about
    0.70
     अबाउट
    0.69
     mehr
    0.67
     apie
    0.67
    Act Density 0.023%

    No Known Activations