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

    Neuronpedia

    INDEX
    Explanations

    introduction phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     escolas
    0.51
     중심
    0.50
    學校
    0.48
     လူ
    0.46
     criminality
    0.46
     individualism
    0.44
     करिकुलम
    0.43
     palavras
    0.43
     szkoły
    0.43
     борьбы
    0.43
    POSITIVE LOGITS
     cybersecurity
    0.44
    新
    0.43
    an
    0.41
    vet
    0.41
    B
    0.41
    ew
    0.41
     environmental
    0.41
    V
    0.40
     rejuven
    0.40
     troubleshooting
    0.39
    Act Density 0.003%

    No Known Activations