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

    Neuronpedia

    INDEX
    Explanations

    Non-English language texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    家喻户
    -0.07
    linux
    -0.07
     proves
    -0.07
    �
    -0.07
     Tes
    -0.06
    ชวน
    -0.06
    Alamat
    -0.06
     עוס
    -0.06
    各省
    -0.06
    渝
    -0.06
    POSITIVE LOGITS
    command
    0.08
     bracelet
    0.07
     belongings
    0.07
     nå
    0.07
    _dy
    0.07
     rake
    0.07
     SYN
    0.07
     requisite
    0.07
     정도
    0.07
    要闻
    0.07
    Act Density 0.018%

    No Known Activations