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

    Neuronpedia

    INDEX
    Explanations

    Cyber security vulnerabilities

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     almost
    -0.09
    WithTitle
    -0.07
    пер
    -0.07
     تقوم
    -0.07
    Middle
    -0.07
    并不多
    -0.07
    -rounded
    -0.06
    vero
    -0.06
    -double
    -0.06
    🕸
    -0.06
    POSITIVE LOGITS
     Counts
    0.07
    工业园区
    0.07
     Bars
    0.07
    下发
    0.07
     concerns
    0.06
    没收
    0.06
     investments
    0.06
     tutorials
    0.06
     szczeg
    0.06
     Ella
    0.06
    Act Density 0.092%

    No Known Activations