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

    Neuronpedia

    INDEX
    Explanations

    IBM

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convincing
    -0.08
    Workers
    -0.07
    み
    -0.07
     граф
    -0.07
     Dialogue
    -0.07
     coloring
    -0.06
     Billion
    -0.06
     Vitamin
    -0.06
     approve
    -0.06
    èmes
    -0.06
    POSITIVE LOGITS
     Гар
    0.07
    "}}↵
    0.07
    .ค
    0.07
    _cores
    0.06
     दर
    0.06
     söz
    0.06
    /animate
    0.06
     리
    0.06
     �
    0.06
     мер
    0.06
    Act Density 0.027%

    No Known Activations