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

    Neuronpedia

    INDEX
    Explanations

    code, data, miscellaneous text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .generated
    -0.07
     Redirect
    -0.06
     دانلود
    -0.06
    خف
    -0.06
    ungalow
    -0.06
     sustaining
    -0.06
     (_.
    -0.06
     holdings
    -0.06
     borç
    -0.06
    _quantity
    -0.06
    POSITIVE LOGITS
    ropa
    0.07
     grandmother
    0.07
     fe
    0.07
    اع
    0.07
    xin
    0.06
    dney
    0.06
    DIFF
    0.06
    ={↵
    0.06
    -ни
    0.06
    emme
    0.06
    Act Density 0.000%

    No Known Activations