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

    Neuronpedia

    INDEX
    Explanations

    Code and data fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Duterte
    -0.06
     Austrian
    -0.06
    ORITY
    -0.06
    ümüz
    -0.06
    .Download
    -0.06
     BLUE
    -0.06
    ARRY
    -0.06
    professional
    -0.06
    ''''
    -0.06
    가능
    -0.06
    POSITIVE LOGITS
    (links
    0.08
     セ
    0.07
    ividad
    0.06
    _forms
    0.06
    ϊ
    0.06
    059
    0.06
    ={!
    0.06
     エ
    0.06
     Apollo
    0.06
    _reduction
    0.06
    Act Density 0.046%

    No Known Activations