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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEAN
    -0.06
     parler
    -0.06
    Many
    -0.06
    obble
    -0.06
     इन
    -0.06
     onPause
    -0.06
     жит
    -0.06
    AnimationsModule
    -0.06
    	bl
    -0.06
    webkit
    -0.06
    POSITIVE LOGITS
     сп
    0.07
     per
    0.07
     aggress
    0.07
    学
    0.06
    ipeg
    0.06
     prefers
    0.06
     forecasting
    0.06
     έχ
    0.06
     Scottish
    0.06
    學
    0.06
    Act Density 0.006%

    No Known Activations