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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਿਰ
    0.43
    ibh
    0.41
    akiem
    0.41
    ≐
    0.40
    }'],
    0.39
    štu
    0.39
     mniej
    0.39
    าราง
    0.38
     muze
    0.37
    eszcze
    0.36
    POSITIVE LOGITS
    Motor
    0.45
    October
    0.43
     अक्टूबर
    0.43
     work
    0.43
     everyone
    0.41
    work
    0.39
     motor
    0.39
    (\
    0.38
    Images
    0.38
     October
    0.38
    Act Density 0.000%

    No Known Activations