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

    Neuronpedia

    INDEX
    Explanations

    code generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LEG
    -0.07
    lub
    -0.07
    Controllers
    -0.06
     recovery
    -0.06
    _height
    -0.06
    word
    -0.06
     Bail
    -0.06
    needs
    -0.06
     blok
    -0.06
    locate
    -0.06
    POSITIVE LOGITS
     assigns
    0.06
     (;;
    0.06
     withdrew
    0.06
    iế
    0.06
    _Native
    0.06
     Attribution
    0.06
    技能
    0.06
     Midwest
    0.06
    	plt
    0.06
    �
    0.06
    Act Density 0.046%

    No Known Activations