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

    Neuronpedia

    INDEX
    Explanations

    addressing problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     excitement
    0.80
    機
    0.73
    luxury
    0.72
     siebie
    0.70
    Relax
    0.70
     détente
    0.70
    बैक
    0.69
    机
    0.68
     relief
    0.68
     relax
    0.66
    POSITIVE LOGITS
     Close
    0.78
     close
    0.73
    Close
    0.73
    close
    0.69
     מער
    0.69
     Worldwide
    0.68
     Closed
    0.67
     Verhalten
    0.66
    在全球
    0.64
     societies
    0.62
    Act Density 0.179%

    No Known Activations