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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sin
    0.54
     say
    0.54
     genes
    0.52
     repeat
    0.52
     who
    0.51
     stress
    0.51
     weather
    0.50
     you
    0.50
     sporting
    0.50
     conf
    0.49
    POSITIVE LOGITS
    apie
    0.56
     قاعدة
    0.55
     zacz
    0.55
     při
    0.55
     вперед
    0.54
     уника
    0.52
    щини
    0.52
    ğaz
    0.52
     оби
    0.52
     शक्तिशाली
    0.52
    Act Density 0.000%

    No Known Activations