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

    Neuronpedia

    INDEX
    Explanations

    explain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utr
    -0.07
     subjects
    -0.07
     Jahre
    -0.07
     feet
    -0.07
     electroly
    -0.06
    _CHOICES
    -0.06
     submitted
    -0.06
    .allocate
    -0.06
     offenses
    -0.06
    _Y
    -0.06
    POSITIVE LOGITS
    _GRANTED
    0.06
    龙
    0.06
    毕业
    0.06
     hepsi
    0.06
    .history
    0.06
     Thank
    0.06
    BarItem
    0.06
     giác
    0.06
    edback
    0.06
    غات
    0.06
    Act Density 0.019%

    No Known Activations