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

    Neuronpedia

    INDEX
    Explanations

    chatbot conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sacrificed
    -0.08
    	ctx
    -0.07
     sacrifice
    -0.07
     обр
    -0.07
    Dst
    -0.07
     amaç
    -0.07
    勿
    -0.07
    signature
    -0.07
     signature
    -0.07
    рада
    -0.07
    POSITIVE LOGITS
     refine
    0.11
     refin
    0.11
     Refin
    0.11
     Further
    0.10
    进一步
    0.10
     refining
    0.10
     continuar
    0.09
     refinement
    0.09
    続きを
    0.09
     further
    0.09
    Act Density 0.016%

    No Known Activations