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

    Neuronpedia

    INDEX
    Explanations

    errors in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Highland
    -0.07
    „A
    -0.06
    amples
    -0.06
    (keyword
    -0.06
    asier
    -0.06
    “How
    -0.06
    .Dev
    -0.06
    (Build
    -0.06
     specifying
    -0.06
    _constraint
    -0.06
    POSITIVE LOGITS
     مرتبط
    0.07
     微
    0.06
    ()<<
    0.06
     نگهد
    0.06
     devast
    0.06
    痛
    0.06
     Fuji
    0.06
     건강
    0.06
    诉
    0.06
     strategist
    0.06
    Act Density 0.004%

    No Known Activations