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

    Neuronpedia

    INDEX
    Explanations

    explanations: why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potete
    0.86
     YOU
    0.79
     можете
    0.75
     LA
    0.74
     You
    0.73
    Downloads
    0.73
    Puedes
    0.73
    ？
    0.73
     you
    0.72
     LO
    0.72
    POSITIVE LOGITS
    acketing
    0.71
     effectivement
    0.68
    kipun
    0.68
     étant
    0.67
     réflexion
    0.66
     incorrect
    0.65
    incorrect
    0.65
     extrêmement
    0.65
    实际上
    0.64
     antagonism
    0.64
    Act Density 0.003%

    No Known Activations