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

    Neuronpedia

    INDEX
    Explanations

    positioning or interviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     micron
    0.40
     Myth
    0.40
     vocabulary
    0.39
     DY
    0.39
     phức
    0.39
     degassing
    0.39
     violence
    0.39
    暴力
    0.39
     scalability
    0.38
     venture
    0.37
    POSITIVE LOGITS
     records
    0.44
     públic
    0.44
    公开
    0.44
     таксама
    0.44
     Records
    0.42
     записа
    0.42
     RECORDS
    0.41
    udem
    0.41
    yty
    0.41
     natomiast
    0.40
    Act Density 0.001%

    No Known Activations