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

    Neuronpedia

    INDEX
    Explanations

    accessing `message` or `text`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    քում
    0.39
    жении
    0.38
    นด์
    0.38
    öpf
    0.37
    ᄅ
    0.37
     کنار
    0.37
    軻
    0.37
    佲
    0.37
     गा
    0.37
    വര്‍
    0.37
    POSITIVE LOGITS
     p
    0.38
     Ut
    0.38
     babys
    0.38
    ilen
    0.37
     from
    0.37
     Qxe
    0.37
     s
    0.36
     gone
    0.36
     fai
    0.36
     tam
    0.35
    Act Density 0.002%

    No Known Activations