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

    Neuronpedia

    INDEX
    Explanations

    safety concerns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pad
    -0.08
    bu
    -0.07
     powerless
    -0.07
    빚
    -0.07
    𝕀
    -0.07
    vis
    -0.07
    .embed
    -0.06
     Paul
    -0.06
    积累
    -0.06
    败
    -0.06
    POSITIVE LOGITS
     бер
    0.07
    ="<<
    0.07
    Annotation
    0.07
    YLON
    0.07
     Steak
    0.07
     Spin
    0.07
    تكلم
    0.07
    合资
    0.07
    clin
    0.07
     chauff
    0.07
    Act Density 0.059%

    No Known Activations