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

    Neuronpedia

    INDEX
    Explanations

    research difficulties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    统
    -0.07
     Warning
    -0.06
    十六
    -0.06
     disarm
    -0.06
    Sanders
    -0.06
    .Utility
    -0.06
     Switch
    -0.06
     minimum
    -0.06
    てる
    -0.06
     güçlü
    -0.06
    POSITIVE LOGITS
    ประเทศ
    0.06
    енз
    0.06
    ritable
    0.06
     francaise
    0.06
    템
    0.06
     nilai
    0.06
    ταν
    0.06
     知
    0.06
     jednání
    0.06
    .position
    0.06
    Act Density 0.073%

    No Known Activations