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

    Neuronpedia

    INDEX
    Explanations

    Uncommon strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     этих
    -0.08
     televis
    -0.07
    姐
    -0.07
     tình
    -0.07
     Tình
    -0.07
    慌
    -0.07
    全文
    -0.07
    erg
    -0.07
    ên
    -0.07
    .what
    -0.07
    POSITIVE LOGITS
    ⓕ
    0.07
     jq
    0.07
     trolling
    0.07
    キッチン
    0.07
     schematic
    0.06
    탶
    0.06
     ноч
    0.06
    纳米
    0.06
     quận
    0.06
     chuckled
    0.06
    Act Density 0.004%

    No Known Activations