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

    Neuronpedia

    INDEX
    Explanations

    ordered collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Budget
    -0.07
     budget
    -0.07
    [T
    -0.06
     bury
    -0.06
     Software
    -0.06
    тр
    -0.06
    _holder
    -0.06
    [__
    -0.06
     Global
    -0.06
     Kang
    -0.06
    POSITIVE LOGITS
    DirectoryName
    0.06
    endoza
    0.06
    veyor
    0.06
    ่าเป
    0.06
    سات
    0.06
    이었
    0.06
    Replacement
    0.06
    —"
    0.06
     Cinder
    0.06
    \Repositories
    0.06
    Act Density 0.320%

    No Known Activations