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

    Neuronpedia

    INDEX
    Explanations

    free for you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hiểm
    0.40
     babel
    0.40
    plier
    0.37
     утра
    0.37
     жак
    0.36
    墉
    0.36
    quers
    0.36
    QUESTIONS
    0.36
     குறித்த
    0.36
    getProgress
    0.36
    POSITIVE LOGITS
     liberate
    0.51
    coast
    0.50
    free
    0.49
     frees
    0.49
    自由に
    0.48
     liberated
    0.48
    democracy
    0.47
     freeing
    0.46
     liberating
    0.46
    freedom
    0.45
    Act Density 0.034%

    No Known Activations