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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baru
    -0.07
    .booking
    -0.07
     Hulu
    -0.07
    ेखत
    -0.06
     Поп
    -0.06
     다운받
    -0.06
     hardness
    -0.06
     denen
    -0.06
    .AllowGet
    -0.06
    持ち
    -0.06
    POSITIVE LOGITS
    ськ
    0.07
    ").↵↵
    0.07
    ("//
    0.06
    thes
    0.06
     ministries
    0.06
     tow
    0.06
    Instruction
    0.06
    [word
    0.06
    ký
    0.06
    ิส
    0.06
    Act Density 0.010%

    No Known Activations