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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tests
    -0.06
     methodology
    -0.06
    들이
    -0.06
     Queue
    -0.06
    İTESİ
    -0.06
    engineering
    -0.06
    .*;
↵
↵
    -0.06
    äm
    -0.06
    isc
    -0.06
    kiego
    -0.06
    POSITIVE LOGITS
     CBS
    0.07
     —
    0.06
    <Category
    0.06
     pf
    0.06
    ('../../
    0.06
    _Tr
    0.06
     Creating
    0.06
    -xs
    0.06
     --↵
    0.06
     **/↵↵
    0.06
    Act Density 0.067%

    No Known Activations