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

    Neuronpedia

    INDEX
    Explanations

    programming elements multilingually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒋾
    0.51
    वीण
    0.49
    gleichen
    0.47
    ಂಡ
    0.45
     आंतरिक
    0.44
     হইয়াছিলেন
    0.44
     percolation
    0.43
    رین
    0.43
     ⏮
    0.43
    🥸
    0.43
    POSITIVE LOGITS
     it
    0.50
    它
    0.47
    port
    0.41
     its
    0.41
     Aut
    0.39
    其
    0.39
    ville
    0.39
    m
    0.38
    t
    0.38
     ĝi
    0.38
    Act Density 0.001%

    No Known Activations