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

    Neuronpedia

    INDEX
    Explanations

    performance and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    をお願い
    0.39
    瑛
    0.37
     happening
    0.37
    калә
    0.37
    getServer
    0.36
    昭
    0.36
    在美国
    0.36
     영향을
    0.36
     resonate
    0.35
    ränkt
    0.35
    POSITIVE LOGITS
     anc
    0.46
    Mobs
    0.41
    Downward
    0.40
    вает
    0.37
     coffers
    0.37
     beams
    0.37
    haut
    0.37
     δι
    0.37
     rodents
    0.37
     ance
    0.36
    Act Density 0.000%

    No Known Activations