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

    Neuronpedia

    INDEX
    Explanations

    Instructions/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Syntax
    -0.07
    체
    -0.06
    ович
    -0.06
     Kang
    -0.06
     hind
    -0.06
    rub
    -0.06
    웠
    -0.06
    帯
    -0.06
    маз
    -0.06
    ни
    -0.06
    POSITIVE LOGITS
     '--
    0.08
     HISTORY
    0.07
    rary
    0.06
     '/';↵
    0.06
    '});↵
    0.06
    uintptr
    0.06
     nue
    0.06
    xm
    0.06
    _IMAGE
    0.06
     Arch
    0.06
    Act Density 0.083%

    No Known Activations