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

    Neuronpedia

    INDEX
    Explanations

    il

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     факт
    -0.07
    "In
    -0.07
     fois
    -0.07
     toItem
    -0.06
    ětí
    -0.06
     }↵↵↵
    -0.06
    #if
    -0.06
    
    -0.06
    _ptrs
    -0.06
     })↵↵
    -0.06
    POSITIVE LOGITS
     aument
    0.07
     eighty
    0.06
    bear
    0.06
    .Api
    0.06
    ющих
    0.06
    (AP
    0.06
    ront
    0.06
    vironment
    0.06
    -focused
    0.06
    reduce
    0.06
    Act Density 0.000%

    No Known Activations