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

    Neuronpedia

    INDEX
    Explanations

    purification processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     демон
    -0.07
    šti
    -0.07
    .Controllers
    -0.07
     Rig
    -0.07
    _char
    -0.06
    یزی
    -0.06
    CppCodeGen
    -0.06
     Harvey
    -0.06
     terminology
    -0.06
    че
    -0.06
    POSITIVE LOGITS
     itir
    0.06
     нож
    0.06
    ayım
    0.06
     osobních
    0.06
    üph
    0.06
    udu
    0.06
     ті
    0.06
    apters
    0.06
     působ
    0.06
    建议
    0.06
    Act Density 0.049%

    No Known Activations