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

    Neuronpedia

    INDEX
    Explanations

    internet security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cursor
    -0.09
     ощущения
    -0.08
    esom
    -0.08
     weekly
    -0.08
     Weekly
    -0.08
     सप्ताह
    -0.07
     הדברים
    -0.07
     чаще
    -0.07
     semanal
    -0.07
     häufig
    -0.07
    POSITIVE LOGITS
     malicious
    0.13
    窥
    0.11
     unauthorized
    0.11
     зло
    0.10
     anyone
    0.10
    偷窥
    0.10
     someone
    0.10
    誰
    0.10
    Unauthorized
    0.10
    非法
    0.10
    Act Density 0.024%

    No Known Activations