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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    keys
    -0.07
    ni
    -0.07
    µ
    -0.07
    HR
    -0.07
    镁
    -0.07
    ões
    -0.07
     complicated
    -0.06
    Ham
    -0.06
     무엇
    -0.06
    cis
    -0.06
    POSITIVE LOGITS
    (detail
    0.07
    .imwrite
    0.07
     Turnbull
    0.06
     infile
    0.06
    ROOT
    0.06
     אית
    0.06
     CONVERT
    0.06
    (itemView
    0.06
    䴀
    0.06
    ！');↵
    0.06
    Act Density 0.148%

    No Known Activations