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

    Neuronpedia

    INDEX
    Explanations

    error messages and script output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    টি
    1.36
    م
    1.32
    รียม
    1.31
     potência
    1.27
    vertexBuffer
    1.27
     óleo
    1.27
     vitória
    1.25
    LinkId
    1.22
    𝘴
    1.22
    مپ
    1.22
    POSITIVE LOGITS
     unfit
    1.00
     Galaxy
    0.95
     advised
    0.95
    슨
    0.90
     advising
    0.90
     galaxy
    0.88
    EST
    0.87
     опор
    0.87
    ರ್ಷ
    0.84
    ی
    0.83
    Act Density 0.002%

    No Known Activations