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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Momentum
    -0.07
     Adoption
    -0.06
     Ug
    -0.06
     Briggs
    -0.06
    ndo
    -0.06
     intox
    -0.06
     Fuse
    -0.06
    _Speed
    -0.06
     embrace
    -0.06
    _management
    -0.06
    POSITIVE LOGITS
     antioxidant
    0.07
                                    
    0.06
    _pri
    0.06
     ass
    0.06
     поверхности
    0.06
    ostringstream
    0.06
     gameOver
    0.06
    houette
    0.06
    -plan
    0.06
    石
    0.06
    Act Density 0.111%

    No Known Activations